© 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. 1-RES-JB
    11. 16413
    Prev
    Next
    INDEX
    Explanations

    historical references and events

    oai_token-act-pair · gpt-3.5-turbo

    references to historical figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Shares
    -0.72
    Politics
    -0.70
    Viol
    -0.69
    icio
    -0.68
    Ble
    -0.67
     Squirrel
    -0.67
    rav
    -0.66
    Normally
    -0.66
    Talk
    -0.66
    gets
    -0.65
    POSITIVE LOGITS
     inscribed
    0.95
     inscription
    0.89
     Ottoman
    0.89
     Tud
    0.87
     Seym
    0.85
     manuscripts
    0.85
     Frie
    0.85
     engraved
    0.84
     archae
    0.83
    otype
    0.82
    Activations Density 0.831%

    No Known Activations