© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 16419
    Prev
    Next
    INDEX
    Explanations

    mentions of specific food items

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antry
    -0.79
    kefeller
    -0.77
    ONEY
    -0.74
    WORK
    -0.73
    igham
    -0.71
    agher
    -0.71
    alions
    -0.70
    azeera
    -0.69
    etheus
    -0.69
    anmar
    -0.67
    POSITIVE LOGITS
     Vide
    0.70
     Flavoring
    0.65
     Rhino
    0.65
    angered
    0.65
    >>\
    0.64
    stall
    0.64
    uay
    0.64
     Lac
    0.63
     violet
    0.61
     hier
    0.61
    Activations Density 0.000%

    No Known Activations