© 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. 32004
    Prev
    Next
    INDEX
    Explanations

    names of individuals named "Tony"

    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
    447
    +0.21
    0.9%
    139
    +0.12
    0.5%
    415
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.21
    0.04
    706
    +0.12
    0.11
    418
    +0.11
    0.10
    Negative Logits
    INESS
    -0.97
    ãģ¦
    -0.82
    baugh
    -0.77
    ername
    -0.76
    Magikarp
    -0.76
    words
    -0.74
    20439
    -0.73
    doors
    -0.73
    BOOK
    -0.72
    cipline
    -0.72
    POSITIVE LOGITS
     Blair
    1.02
     Abbott
    0.99
     Sop
    0.99
     Romo
    0.93
     Hawk
    0.92
    neau
    0.88
     Stark
    0.86
     Tony
    0.85
     Cliff
    0.80
     Fernand
    0.79
    Activations Density 7.258%

    No Known Activations