© 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. 7-RES-JB
    11. 18074
    Prev
    Next
    INDEX
    Explanations

    references to legal documents or historical events, particularly declarations and statements

    oai_token-act-pair · gpt-3.5-turbo

    references to key historical documents, particularly declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ROR
    -0.68
    iences
    -0.67
    icago
    -0.66
    ruciating
    -0.66
    OTOS
    -0.66
    committee
    -0.66
    ionage
    -0.64
    elve
    -0.64
    cffff
    -0.63
    alez
    -0.63
    POSITIVE LOGITS
    aration
    0.98
    arations
    0.88
     declaration
    0.88
    ignty
    0.80
     Decl
    0.73
    ension
    0.72
     declaring
    0.72
     decl
    0.71
     declares
    0.71
    Decl
    0.70
    Activations Density 0.048%

    No Known Activations