© 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. 13295
    Prev
    Next
    INDEX
    Explanations

    questions or statements with the word "want to"

    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
    508
    +0.14
    0.5%
    536
    +0.14
    0.5%
    634
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.14
    0.04
    634
    +0.14
    0.06
    244
    +0.14
    0.05
    Negative Logits
    errors
    -0.99
    mitter
    -0.95
    sg
    -0.94
    squ
    -0.94
    typ
    -0.93
    iky
    -0.90
    pmwiki
    -0.90
    dq
    -0.89
    alien
    -0.88
    interstitial
    -0.88
    POSITIVE LOGITS
     purposes
    0.97
     sake
    0.92
     to
    0.87
    awaru
    0.86
     fuller
    0.85
     Reloaded
    0.84
    lier
    0.84
     succeed
    0.83
     truly
    0.82
    atell
    0.80
    Activations Density 0.681%

    No Known Activations