© 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. 12936
    Prev
    Next
    INDEX
    Explanations

    mentions of food items and cooking instructions

    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
    699
    +0.11
    0.5%
    718
    +0.11
    0.5%
    513
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.11
    0.18
    754
    +0.11
    0.16
    48
    +0.11
    0.15
    Negative Logits
    ocr
    -0.85
    ouri
    -0.77
    enf
    -0.75
    ored
    -0.74
    utra
    -0.74
    ologically
    -0.71
     Khe
    -0.70
    ocrats
    -0.68
    aeda
    -0.67
    iqueness
    -0.67
    POSITIVE LOGITS
    ½
    0.97
    ï¸ı
    0.91
    ÃĹ
    0.86
    mb
    0.81
     inch
    0.80
     dozen
    0.75
     hour
    0.75
     sided
    0.74
     ½
    0.72
    WER
    0.72
    Activations Density 5.211%

    No Known Activations