© 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 Local
    9. 6-RES_SCL-AJT
    11. 35683
    Prev
    Next
    INDEX
    Explanations

    information related to promotions within organizations or sports teams

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    679
    +0.16
    0.7%
    288
    +0.12
    0.5%
    269
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.21
    575
    +0.12
    0.15
    301
    +0.12
    0.08
    Negative Logits
    ð
    -0.89
    sten
    -0.78
     Refuge
    -0.76
     sequest
    -0.74
    ead
    -0.73
     PRESIDENT
    -0.73
    lv
    -0.72
    mia
    -0.70
    fa
    -0.70
    yah
    -0.68
    POSITIVE LOGITS
    xual
    1.08
    chwitz
    0.86
     promotion
    0.81
     promoted
    0.76
    ISO
    0.76
    SHIP
    0.75
     promotions
    0.75
    stakes
    0.75
    pires
    0.73
    ename
    0.73
    Activations Density 6.000%

    No Known Activations