© 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. 1384
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "bacon" in the text

    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
    421
    +0.07
    0.5%
    101
    +0.07
    0.5%
    706
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.07
    0.01
    232
    +0.07
    0.01
    326
    +0.07
    0.01
    Negative Logits
     horizont
    -0.48
     awa
    -0.48
     proble
    -0.45
     psychiat
    -0.45
     obser
    -0.45
     plent
    -0.44
     aval
    -0.44
     warr
    -0.44
    TPS
    -0.43
     stroke
    -0.43
    POSITIVE LOGITS
    hip
    0.57
    acon
    0.55
    lov
    0.54
    ite
    0.52
    ium
    0.52
    ic
    0.52
    ites
    0.52
    rine
    0.51
    itic
    0.51
    ess
    0.51
    Activations Density 0.059%

    No Known Activations