© 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. 11-RES-JB
    11. 18664
    Prev
    Next
    INDEX
    Explanations

    proposals or plans mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to proposed legislation or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tesy
    -1.02
    ï¸
    -0.88
    nikov
    -0.86
    oso
    -0.85
    wo
    -0.82
    vation
    -0.82
    beit
    -0.80
    cellent
    -0.79
    gettable
    -0.78
    played
    -0.77
    POSITIVE LOGITS
     merger
    1.07
     changes
    1.06
     amendments
    1.06
     amendment
    1.04
     revisions
    1.03
     Parenthood
    1.01
     reforms
    0.98
     solution
    0.97
     redesign
    0.91
     alterations
    0.90
    Activations Density 0.083%

    No Known Activations