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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 40873
    Prev
    Next
    INDEX
    Explanations

    expletives and expressions of frustration or disbelief

    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
    649
    +0.14
    0.6%
    687
    +0.14
    0.6%
    553
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    334
    +0.14
    0.05
    274
    +0.14
    0.07
    497
    +0.12
    0.09
    Negative Logits
    083
    -0.83
    cit
    -0.81
    ufact
    -0.80
    Vert
    -0.76
    Ĭ±
    -0.75
    士
    -0.74
    Joy
    -0.73
    hig
    -0.72
    iku
    -0.71
    vic
    -0.71
    POSITIVE LOGITS
     happened
    0.92
    ?!
    0.88
     else
    0.80
     dude
    0.79
    !?"
    0.78
    !?
    0.77
    ?!"
    0.77
    holes
    0.75
    dar
    0.73
     fuck
    0.72
    Activations Density 4.997%

    No Known Activations