© 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. 39509
    Prev
    Next
    INDEX
    Explanations

    personal experiences and interactions involving trust, betrayal, and resentment

    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
    447
    +0.25
    1.1%
    502
    +0.13
    0.6%
    363
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.25
    0.18
    167
    +0.13
    0.00
    502
    +0.11
    0.12
    Negative Logits
    isite
    -0.84
    ãĥĬ
    -0.79
    awaru
    -0.77
    âĺħ
    -0.76
    zees
    -0.76
    ailand
    -0.75
    istics
    -0.74
     Sabha
    -0.74
    ariat
    -0.73
    iencies
    -0.70
    POSITIVE LOGITS
    ñ
    0.76
    'm
    0.71
     frig
    0.70
     tatt
    0.69
    've
    0.67
     bount
    0.67
     dunno
    0.66
     forget
    0.66
     coer
    0.65
     presume
    0.65
    Activations Density 13.716%

    No Known Activations