© 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. 36539
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals named "Phil" in the text

    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
    213
    +0.16
    0.7%
    447
    +0.14
    0.6%
    289
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.16
    0.06
    712
    +0.14
    0.05
    289
    +0.14
    -0.01
    Negative Logits
    CLASSIFIED
    -1.06
    tenance
    -0.94
    yrinth
    -0.83
    DERR
    -0.83
    erers
    -0.83
    Demand
    -0.74
     TAM
    -0.73
    ãĥ¼ãĥĨãĤ£
    -0.72
    erness
    -0.72
    erer
    -0.71
    POSITIVE LOGITS
    anthrop
    1.64
    istine
    1.54
    andering
    1.25
    adel
    1.25
    oton
    1.20
    harm
    1.19
    onen
    1.17
    onite
    1.16
    ophe
    1.14
    ando
    1.13
    Activations Density 5.628%

    No Known Activations