© 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. 13482
    Prev
    Next
    INDEX
    Explanations

    phrases related to toughness and strength

    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
    301
    +0.15
    0.6%
    339
    +0.12
    0.5%
    240
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.08
    326
    +0.12
    0.07
    232
    +0.09
    0.04
    Negative Logits
    piece
    -0.96
     Emin
    -0.80
    istor
    -0.80
     Cosponsors
    -0.75
    mouth
    -0.74
    pieces
    -0.73
    netflix
    -0.73
    Pool
    -0.71
    pool
    -0.70
     VIDEOS
    -0.69
    POSITIVE LOGITS
    oug
    1.06
    avored
    1.04
    atche
    1.00
    aneers
    0.99
    otten
    0.98
    hest
    0.91
    itives
    0.90
    otiation
    0.86
    assed
    0.86
    atted
    0.81
    Activations Density 1.084%

    No Known Activations