© 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. 12931
    Prev
    Next
    INDEX
    Explanations

    instances of the number "two" in relation to quantity or sequences

    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
    +0.22
    0.9%
    393
    +0.15
    0.6%
    116
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.22
    0.18
    159
    +0.15
    0.11
    608
    +0.11
    0.16
    Negative Logits
    ugu
    -0.80
    asta
    -0.79
     Caption
    -0.74
    ashtra
    -0.73
    lus
    -0.73
    rir
    -0.72
    amaru
    -0.70
    ICLE
    -0.69
    ook
    -0.67
    urden
    -0.66
    POSITIVE LOGITS
     thirds
    1.69
     dozen
    1.24
     halves
    1.12
     hundred
    1.12
     weeks
    1.11
    fold
    1.10
    teenth
    1.01
    nd
    0.97
    een
    0.95
     thousand
    0.94
    Activations Density 9.737%

    No Known Activations