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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8425
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics and legislation

    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
    447
    +0.17
    0.9%
    393
    +0.17
    0.9%
    266
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.17
    0.08
    266
    +0.17
    0.34
    101
    +0.16
    0.32
    Negative Logits
    emale
    -0.76
    retty
    -0.73
    kw
    -0.66
    agra
    -0.65
    odan
    -0.64
    undown
    -0.61
    inkle
    -0.60
    unky
    -0.60
    ãģ®æ
    -0.59
    igil
    -0.57
    POSITIVE LOGITS
     largeDownload
    0.60
     Aval
    0.59
     Rouhani
    0.59
     Pwr
    0.56
     retracted
    0.54
    CVE
    0.54
     bol
    0.52
     grate
    0.51
     threatened
    0.51
     crypt
    0.51
    Activations Density 14.098%

    No Known Activations