© 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. 5811
    Prev
    Next
    INDEX
    Explanations

    recruitment-related terms and information

    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
    288
    +0.23
    0.8%
    604
    +0.18
    0.6%
    679
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.08
    604
    +0.18
    0.04
    575
    +0.16
    0.06
    Negative Logits
     Oo
    -1.00
     prevail
    -0.95
    lihood
    -0.91
    oeuv
    -0.90
     Minute
    -0.89
    plays
    -0.87
    gur
    -0.86
    ijk
    -0.83
    gard
    -0.82
    zz
    -0.81
    POSITIVE LOGITS
    glers
    1.12
     recruits
    1.06
    ãĥ¼ãĥĨãĤ£
    1.00
    ments
    0.98
    eering
    0.95
    LES
    0.93
     recruit
    0.93
    anooga
    0.92
    inant
    0.92
    untarily
    0.92
    Activations Density 0.735%

    No Known Activations