© 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. 32806
    Prev
    Next
    INDEX
    Explanations

    statements of truth or accuracy

    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
    +0.23
    1.0%
    642
    +0.10
    0.4%
    677
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.23
    0.14
    580
    +0.10
    0.10
    274
    +0.10
    0.09
    Negative Logits
    adish
    -0.81
    Pages
    -0.80
     Sunder
    -0.72
    isoft
    -0.71
    uty
    -0.69
    vernment
    -0.69
    IDs
    -0.69
    ody
    -0.68
    uled
    -0.68
    acco
    -0.67
    POSITIVE LOGITS
    terday
    0.96
     believer
    0.78
     regardless
    0.76
     believers
    0.75
     Nationwide
    0.71
    rill
    0.70
    ãĥ¼ãĥĨ
    0.69
     irrespective
    0.68
    polit
    0.67
    ually
    0.67
    Activations Density 8.603%

    No Known Activations