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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5263
    Prev
    Next
    INDEX
    Explanations

    companies listed on the S&P 500

    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
    146
    +0.20
    0.6%
    241
    +0.17
    0.5%
    543
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.20
    0.10
    398
    +0.17
    0.07
    543
    +0.17
    0.07
    Negative Logits
    dyl
    -1.33
    gie
    -1.17
    taboola
    -1.15
    usra
    -1.14
    yn
    -1.12
    byn
    -1.09
    paio
    -1.01
    oslov
    -0.99
    alogue
    -0.95
     Kasich
    -0.95
    POSITIVE LOGITS
    Corp
    1.45
    ®
    1.25
     Publishing
    1.19
     Digest
    1.14
     Dome
    1.14
    INESS
    1.14
    Draft
    1.13
     Presents
    1.13
     Awards
    1.12
     Headquarters
    1.12
    Activations Density 1.661%

    No Known Activations