© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 9580
    Prev
    Next
    INDEX
    Explanations

    words related to metabolism and metabolic processes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Virgin
    -0.77
     Torn
    -0.74
     Bans
    -0.72
    holder
    -0.71
     Panasonic
    -0.69
    llah
    -0.68
    anamo
    -0.68
    zilla
    -0.66
     Pon
    -0.66
     Cthulhu
    -0.64
    POSITIVE LOGITS
     enzyme
    1.23
     enzymes
    1.23
     inhibitors
    1.15
     inhibitor
    1.08
     metabolism
    0.98
     inhibition
    0.96
    etics
    0.92
     metabol
    0.88
    active
    0.84
     enz
    0.82
    Activations Density 0.059%

    No Known Activations