© 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. 11797
    Prev
    Next
    INDEX
    Explanations

    email header information such as sender, receiver, dates, and subjects

    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
    +0.23
    0.8%
    187
    +0.15
    0.5%
    506
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.23
    0.05
    640
    +0.15
    0.05
    145
    +0.13
    0.03
    Negative Logits
     veter
    -1.21
    icut
    -0.92
     subdiv
    -0.92
     puberty
    -0.90
    psey
    -0.87
     wisely
    -0.85
    cipline
    -0.83
     gestation
    -0.83
    glomer
    -0.83
     zoom
    -0.82
    POSITIVE LOGITS
     CTR
    1.13
    "]=>
    0.88
    Online
    0.88
    PsyNetMessage
    0.87
     Received
    0.86
    Mail
    0.86
    Unknown
    0.85
    none
    0.84
    Date
    0.84
    enture
    0.84
    Activations Density 0.345%

    No Known Activations