© 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. 31910
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or activities taken by individuals

    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%
    715
    +0.12
    0.5%
    183
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.21
    0.16
    715
    +0.12
    0.12
    354
    +0.12
    0.10
    Negative Logits
    ²¾
    -0.90
    ricular
    -0.87
    orthodox
    -0.83
    versible
    -0.81
    ignty
    -0.81
    bons
    -0.80
     tiss
    -0.79
    relevant
    -0.79
    ikhail
    -0.78
    icon
    -0.77
    POSITIVE LOGITS
     undone
    1.05
     forth
    1.01
     ashore
    0.98
     hither
    0.94
     INTO
    0.93
     into
    0.92
     up
    0.88
     out
    0.86
     WRITE
    0.83
     closer
    0.81
    Activations Density 10.097%

    No Known Activations