© 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. 1205
    Prev
    Next
    INDEX
    Explanations

    file-related terms or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    rosso
    -0.91
    ¥µ
    -0.82
    asy
    -0.70
    ghai
    -0.69
     idols
    -0.68
    agonists
    -0.67
    hops
    -0.67
    obia
    -0.64
     soph
    -0.63
     Arist
    -0.63
    POSITIVE LOGITS
     file
    3.65
     files
    2.66
    file
    2.65
     File
    2.61
    File
    2.46
     FILE
    2.25
     Files
    1.97
    FILE
    1.84
    files
    1.79
     filename
    1.74
    Activations Density 0.010%

    No Known Activations