© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 3499
    Prev
    Next
    INDEX
    Explanations

    words related to absorption of various substances

    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
    339
    +0.24
    0.8%
    288
    +0.18
    0.6%
    571
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.24
    0.13
    665
    +0.18
    0.08
    339
    +0.14
    0.06
    Negative Logits
    OPER
    -0.97
    HQ
    -0.95
    eways
    -0.92
    achine
    -0.89
    tera
    -0.85
    eq
    -0.85
    asio
    -0.85
    perm
    -0.85
    Northern
    -0.82
     Violence
    -0.82
    POSITIVE LOGITS
    ibles
    1.11
    uates
    1.08
    rates
    1.04
    hene
    1.03
    ugh
    1.02
     Takeru
    1.00
    rative
    0.96
    aneous
    0.96
    ients
    0.94
    rating
    0.94
    Activations Density 1.666%

    No Known Activations