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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 4877
    Prev
    Next
    INDEX
    Explanations

    phrases related to political parties and leaders

    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
    311
    +0.14
    0.7%
    288
    +0.12
    0.6%
    447
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.14
    -0.01
    8
    +0.12
    0.11
    165
    +0.12
    0.04
    Negative Logits
    soDeliveryDate
    -0.66
    INESS
    -0.65
    ORED
    -0.64
     guiActiveUnfocused
    -0.63
     MFT
    -0.61
     Welch
    -0.61
     externalToEVAOnly
    -0.59
    ãģ®éŃĶ
    -0.58
    士
    -0.57
     Fenrir
    -0.56
    POSITIVE LOGITS
    rica
    1.10
    onso
    0.99
    rika
    0.96
    raid
    0.94
    rican
    0.90
    icion
    0.89
    rik
    0.87
    ghan
    0.87
    resh
    0.85
    raction
    0.85
    Activations Density 7.237%

    No Known Activations