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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14258
    Prev
    Next
    INDEX
    Explanations

    health and wellness tips related to relaxation, sleeping, and medical remedies

    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
    575
    +0.13
    0.6%
    274
    +0.13
    0.6%
    569
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.10
    326
    +0.13
    0.08
    274
    +0.11
    0.06
    Negative Logits
    ADRA
    -0.89
    ledge
    -0.86
    atters
    -0.81
    yll
    -0.81
    URA
    -0.80
    ãĤ¢ãĥ«
    -0.79
    ership
    -0.76
     Ago
    -0.74
    ãĥı
    -0.74
    âĸĪâĸĪâĸĪâĸĪ
    -0.73
    POSITIVE LOGITS
     depreciation
    0.83
     accrued
    0.76
     bonus
    0.71
     killers
    0.67
     millenn
    0.67
     sanction
    0.66
     creep
    0.65
     payoff
    0.65
     indemn
    0.64
     deducted
    0.64
    Activations Density 1.133%

    No Known Activations