© 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. 32567
    Prev
    Next
    INDEX
    Explanations

    fictional characters and elements in texts

    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
    +0.14
    0.6%
    288
    +0.13
    0.6%
    151
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.22
    151
    +0.13
    0.17
    568
    +0.13
    0.05
    Negative Logits
    ktop
    -0.98
    hammad
    -0.88
    xual
    -0.81
    annis
    -0.80
    ereo
    -0.76
    wx
    -0.75
    arching
    -0.73
    Da
    -0.73
    KI
    -0.71
    Ag
    -0.71
    POSITIVE LOGITS
    ized
    1.10
    ization
    0.95
    ised
    0.94
    ties
    0.93
    izing
    0.89
    istically
    0.88
     recre
    0.88
    izable
    0.87
     universes
    0.87
    izations
    0.86
    Activations Density 8.652%

    No Known Activations