© 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. 4045
    Prev
    Next
    INDEX
    Explanations

    statements or quotes within text

    oai_token-act-pair · gpt-3.5-turbo

    references to formal declarations or announcements

    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
    ateurs
    -0.75
    hung
    -0.68
    pots
    -0.65
    downs
    -0.65
    antine
    -0.65
    yards
    -0.64
     Beet
    -0.62
    unn
    -0.62
    uel
    -0.62
     transpl
    -0.61
    POSITIVE LOGITS
     statement
    3.60
     Statement
    2.65
     statements
    2.49
    Statement
    2.45
    statement
    2.29
     Statements
    2.11
     declaration
    1.94
     assertion
    1.60
     proclamation
    1.43
     remark
    1.42
    Activations Density 0.036%

    No Known Activations