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. 416
    Prev
    Next
    INDEX
    Explanations

    statistics and data related to political and social issues

    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
    686
    +0.17
    0.6%
    456
    +0.13
    0.4%
    610
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.17
    0.06
    260
    +0.13
    0.05
    98
    +0.13
    0.05
    Negative Logits
    hement
    -0.96
     Hassan
    -0.90
     Byz
    -0.90
    complex
    -0.88
    mercial
    -0.86
    lement
    -0.86
     Salman
    -0.86
    heng
    -0.84
    utsche
    -0.84
    unct
    -0.84
    POSITIVE LOGITS
     msec
    1.00
    NPR
    1.00
     trillion
    0.92
    ths
    0.91
     cases
    0.90
     percent
    0.89
    âĸĪ
    0.84
    iever
    0.83
     billion
    0.83
     imaginable
    0.82
    Activations Density 0.475%

    No Known Activations