© 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. 13976
    Prev
    Next
    INDEX
    Explanations

    words related to limitations or restrictions, especially in a regulatory or control context

    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
    1.2%
    311
    +0.12
    0.5%
    497
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.26
    -0.04
    225
    +0.12
    0.08
    288
    +0.11
    0.18
    Negative Logits
    FORE
    -0.84
    ashington
    -0.77
    psc
    -0.74
    tom
    -0.73
    bench
    -0.70
    orah
    -0.69
    tes
    -0.69
    hoe
    -0.68
    rouse
    -0.68
    Sham
    -0.68
    POSITIVE LOGITS
    ively
    0.90
     restricting
    0.89
     restricted
    0.86
     restricts
    0.86
     restrictions
    0.85
     imposed
    0.83
    ricted
    0.83
     restrictive
    0.80
    ions
    0.79
     cooker
    0.79
    Activations Density 7.537%

    No Known Activations