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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 14008
    Prev
    Next
    INDEX
    Explanations

    information related to financial transactions and legal disputes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    566
    +0.18
    0.7%
    393
    +0.14
    0.5%
    167
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.18
    0.11
    502
    +0.14
    0.10
    566
    +0.13
    0.10
    Negative Logits
    aphael
    -0.84
     Canaver
    -0.80
     Cliff
    -0.78
    math
    -0.77
    heimer
    -0.77
    ³³³³
    -0.76
    icative
    -0.75
     Anat
    -0.74
    lihood
    -0.73
     Schiff
    -0.73
    POSITIVE LOGITS
    've
    1.26
    'd
    1.25
    'll
    1.15
     frequ
    1.08
    Ĥİ
    1.03
     deem
    0.99
     inherited
    0.98
     dearly
    0.98
    arers
    0.95
     wish
    0.94
    Activations Density 1.488%

    No Known Activations