© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 45913
    Prev
    Next
    INDEX
    Explanations

    exclamatory phrases expressing strong emotions

    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
    +0.24
    1.2%
    326
    +0.18
    0.9%
    274
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.24
    0.18
    274
    +0.18
    0.10
    271
    +0.16
    0.06
    Negative Logits
    atories
    -0.74
    oult
    -0.70
    unker
    -0.66
    aldi
    -0.65
     saline
    -0.64
    ativity
    -0.62
    lining
    -0.62
    auld
    -0.61
    reen
    -0.61
     transpl
    -0.61
    POSITIVE LOGITS
    !!!!!
    1.14
    !!!
    1.03
    !!
    0.98
    !/
    0.90
    @#
    0.87
     :-)
    0.84
    9999
    0.83
    !!!!
    0.82
    ?!
    0.82
     Please
    0.78
    Activations Density 5.869%

    No Known Activations