© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 36473
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative actions or mistreatment, specifically focusing on the concept of degradation and humiliation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.09
    0.7%
    447
    +0.07
    0.5%
    624
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.22
    210
    +0.07
    0.04
    724
    +0.06
    0.11
    Negative Logits
    WORK
    -0.56
    soType
    -0.55
    ning
    -0.55
    NING
    -0.49
    soDeliveryDate
    -0.46
    smith
    -0.46
    oker
    -0.45
    ranch
    -0.43
    ark
    -0.43
    bell
    -0.42
    POSITIVE LOGITS
     humiliation
    0.57
     humiliating
    0.57
     degradation
    0.56
     humili
    0.55
     humiliated
    0.53
     degraded
    0.52
    imens
    0.46
    entary
    0.46
     Petty
    0.46
    graded
    0.45
    Activations Density 8.214%

    No Known Activations