© 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. 32274
    Prev
    Next
    INDEX
    Explanations

    multi-word phrases with intense or emotional connotations related to actions or concepts

    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%
    608
    +0.12
    0.6%
    649
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.18
    0.12
    730
    +0.12
    0.09
    649
    +0.10
    0.03
    Negative Logits
    SPONSORED
    -0.73
    enance
    -0.66
    ettes
    -0.63
    iola
    -0.63
    gon
    -0.62
     borne
    -0.61
    sburgh
    -0.60
     Rouse
    -0.59
    ees
    -0.59
    BuyableInstoreAndOnline
    -0.58
    POSITIVE LOGITS
    place
    1.20
    body
    1.02
    ones
    0.99
    how
    0.92
    ONE
    0.81
     semblance
    0.79
     sort
    0.74
     consolation
    0.70
    HOW
    0.69
     guy
    0.69
    Activations Density 8.455%

    No Known Activations