© 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. 3573
    Prev
    Next
    INDEX
    Explanations

    references to software and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific posts or sections within a document

    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
    iazep
    -0.65
    ensibly
    -0.64
    actionDate
    -0.64
    conservancy
    -0.64
    "},"
    -0.62
    cause
    -0.61
    _>
    -0.61
    inventoryQuantity
    -0.60
    ago
    -0.58
    mor
    -0.58
    POSITIVE LOGITS
     we
    0.88
     there
    0.81
     they
    0.78
    ,
    0.75
     alone
    0.72
     THEY
    0.66
     you
    0.64
     it
    0.61
    ,.
    0.60
     entrants
    0.57
    Activations Density 0.238%

    No Known Activations