© 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. 2557
    Prev
    Next
    INDEX
    Explanations

    website domains and technical terms related to internet communication

    oai_token-act-pair · gpt-3.5-turbo

    references to legal terms and situations related to copyright and infringement

    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
     namely
    -0.66
     sparing
    -0.55
     downright
    -0.54
     absolutely
    -0.53
     arous
    -0.53
    etsy
    -0.52
     which
    -0.50
    ainted
    -0.49
    !?"
    -0.49
    nesday
    -0.49
    POSITIVE LOGITS
    ,...
    1.11
    };
    1.05
     };
    1.02
    ,,,,
    0.99
    ?,
    0.99
    ,,
    0.96
    ,
    0.93
    !,
    0.91
    <|endoftext|>
    0.89
    *,
    0.88
    Activations Density 0.410%

    No Known Activations