© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 33080
    Prev
    Next
    INDEX
    Explanations

    adverbs related to the manner in which actions are carried out

    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
    +0.15
    0.7%
    656
    +0.11
    0.6%
    415
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.15
    0.15
    415
    +0.11
    0.06
    554
    +0.11
    -0.10
    Negative Logits
    amins
    -0.89
     GOODMAN
    -0.71
     affinity
    -0.68
    xes
    -0.68
    yip
    -0.66
    iens
    -0.65
    rers
    -0.64
    uers
    -0.63
    Ĵ
    -0.62
    arth
    -0.61
    POSITIVE LOGITS
     tucked
    0.87
     buried
    0.82
     bom
    0.75
     entertained
    0.70
     quietly
    0.69
    quiet
    0.66
     unheard
    0.65
     upstairs
    0.64
     housed
    0.63
     quiet
    0.63
    Activations Density 8.662%

    No Known Activations