© 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. 39626
    Prev
    Next
    INDEX
    Explanations

    statements related to self-improvement and criticism directed at others

    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
    +0.26
    1.3%
    393
    +0.15
    0.8%
    326
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.26
    0.29
    640
    +0.15
    0.27
    745
    +0.11
    -0.14
    Negative Logits
    quickShipAvailable
    -0.66
    Fra
    -0.61
    furt
    -0.60
     Lotus
    -0.60
    lip
    -0.59
    urous
    -0.59
    Choice
    -0.59
    binding
    -0.58
    ById
    -0.57
    alde
    -0.56
    POSITIVE LOGITS
     keep
    0.91
     clarify
    0.88
     rethink
    0.86
     invest
    0.86
     wait
    0.85
     revisit
    0.85
     be
    0.85
     hurry
    0.85
     buy
    0.84
     spend
    0.82
    Activations Density 13.107%

    No Known Activations