© 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. 32010
    Prev
    Next
    INDEX
    Explanations

    present tense verbs that end in 'eth'

    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
    393
    +0.18
    0.9%
    566
    +0.10
    0.5%
    55
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.18
    0.23
    55
    +0.10
    0.23
    393
    +0.09
    0.27
    Negative Logits
    cffff
    -0.79
    osterone
    -0.73
    ĸļ
    -0.71
    aptic
    -0.69
    cies
    -0.68
    uphem
    -0.67
    tions
    -0.65
    enture
    -0.65
    icum
    -0.64
    atures
    -0.64
    POSITIVE LOGITS
     missing
    0.73
     alive
    0.69
     obs
    0.67
     MISS
    0.64
     guilty
    0.63
     invincible
    0.62
     broken
    0.61
     incomplete
    0.61
    ','
    0.61
    olate
    0.60
    Activations Density 8.798%

    No Known Activations