Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45622
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names related to legal disputes or personal testimonies

    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
    128
    +0.13
    0.5%
    447
    +0.11
    0.5%
    326
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.13
    0.57
    447
    +0.11
    0.59
    64
    +0.11
    -0.14
    Negative Logits
    ERO
    -0.83
     Malfoy
    -0.76
    ors
    -0.73
    orsche
    -0.70
    Eat
    -0.69
     Decay
    -0.68
     Strauss
    -0.67
    wn
    -0.67
    arial
    -0.66
     fierce
    -0.65
    POSITIVE LOGITS
    gency
    1.26
    maid
    1.19
    chant
    1.13
    rill
    1.05
    lins
    0.98
     Rouge
    0.95
    cia
    0.94
    ikan
    0.94
    gence
    0.92
    cedes
    0.91
    Activations Density 7.491%

    No Known Activations