© 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. 31909
    Prev
    Next
    INDEX
    Explanations

    adjectives or adverbs related to speed or quickness

    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
    +0.16
    0.6%
    620
    +0.13
    0.5%
    128
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    629
    +0.16
    0.06
    202
    +0.13
    0.07
    128
    +0.12
    0.07
    Negative Logits
    pheus
    -1.03
     Seym
    -1.02
    xual
    -0.93
    cules
    -0.92
    ignty
    -0.91
    vironment
    -0.89
    eryl
    -0.88
    arks
    -0.87
    代
    -0.87
    iverpool
    -0.87
    POSITIVE LOGITS
    idious
    1.71
     paced
    1.53
    ened
    1.36
    eners
    1.34
    ener
    1.15
    cgi
    1.10
    ening
    1.10
     asleep
    1.05
    nesses
    1.02
     enough
    1.01
    Activations Density 5.871%

    No Known Activations