© 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. 1253
    Prev
    Next
    INDEX
    Explanations

    terms related to legal agreements and partnerships

    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
    461
    +0.15
    0.6%
    455
    +0.13
    0.5%
    302
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.15
    0.09
    461
    +0.13
    0.09
    455
    +0.13
    0.11
    Negative Logits
    ixtures
    -0.85
    ģ«
    -0.84
    ranging
    -0.83
    ãĤ¨ãĥ«
    -0.81
    ãĤ¦ãĤ¹
    -0.80
    Els
    -0.79
    sbm
    -0.78
    ãģĻ
    -0.76
    ceptions
    -0.76
    CRIP
    -0.76
    POSITIVE LOGITS
    's
    1.12
     proceeded
    1.03
     succeeded
    1.03
     stumbled
    0.99
     itself
    0.99
     opted
    0.98
     countered
    0.97
     consulted
    0.96
     hesitated
    0.95
     intends
    0.93
    Activations Density 1.803%

    No Known Activations