© 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. 9-RES-JB
    11. 14380
    Prev
    Next
    INDEX
    Explanations

    words related to specific subjects or areas of expertise, possibly technical or specialized

    oai_token-act-pair · gpt-3.5-turbo

    terms related to systems, structures, and organized entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    details
    -0.79
    awatts
    -0.73
    links
    -0.71
    bats
    -0.71
    iencies
    -0.71
    abilities
    -0.69
    ooks
    -0.69
     dstg
    -0.68
     Cosponsors
    -0.68
     loopholes
    -0.68
    POSITIVE LOGITS
     like
    0.87
     standpoint
    0.86
     consisting
    0.82
    ifier
    0.79
     such
    0.79
    uble
    0.73
    epad
    0.73
     capable
    0.73
    worm
    0.72
     surrounded
    0.72
    Activations Density 0.496%

    No Known Activations