© 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
    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. 35139
    Prev
    Next
    INDEX
    Explanations

    names of different comics publishers

    oai_token-act-pair · gpt-3.5-turbo

    the string "Com" regardless of its position in a word

    oai_token-act-pair · gpt-3.5-turboTriggered by @jordan
    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
    167
    +0.18
    0.7%
    447
    +0.17
    0.7%
    314
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    167
    +0.18
    -0.02
    213
    +0.17
    0.05
    503
    +0.13
    0.05
    Negative Logits
     Kubrick
    -0.97
     harbor
    -0.79
     Keynes
    -0.79
     Icelandic
    -0.79
     Mara
    -0.76
     halfway
    -0.76
     Kund
    -0.74
     infringing
    -0.72
     dwar
    -0.72
     Ducks
    -0.71
    POSITIVE LOGITS
    pletion
    1.47
    fortable
    1.46
    pleting
    1.44
    ptroller
    1.43
    mented
    1.37
    plex
    1.36
    puters
    1.32
    rade
    1.29
    ittee
    1.28
    plete
    1.27
    Activations Density 7.239%

    No Known Activations