© 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. 34822
    Prev
    Next
    INDEX
    Explanations

    phrases related to crossing boundaries or lines

    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
    410
    +0.08
    0.5%
    180
    +0.07
    0.5%
    398
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    553
    +0.08
    0.07
    362
    +0.07
    0.11
    35
    +0.07
    0.06
    Negative Logits
    PDATE
    -0.52
    spot
    -0.50
     expended
    -0.50
    LESS
    -0.49
    ufact
    -0.47
     shaping
    -0.46
     tuning
    -0.45
     rebuilt
    -0.43
    EMP
    -0.43
     endors
    -0.43
    POSITIVE LOGITS
     borders
    0.70
     boundaries
    0.69
     bounds
    0.63
    rome
    0.60
    border
    0.58
    danger
    0.56
    Border
    0.56
    agall
    0.56
     continents
    0.53
     fray
    0.52
    Activations Density 13.182%

    No Known Activations