© 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. 4-RES-JB
    11. 12624
    Prev
    Next
    INDEX
    Explanations

    letters in non-English alphabets with specific accents

    oai_token-act-pair · gpt-3.5-turbo

    special characters or unique symbols within the text

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

    No Comments

    Negative Logits
     adolesc
    -0.91
    merce
    -0.90
     carbohyd
    -0.82
    auga
    -0.79
    ufact
    -0.78
    anooga
    -0.75
    ividual
    -0.74
     citiz
    -0.73
     scrut
    -0.70
     suc
    -0.70
    POSITIVE LOGITS
    ×ķ
    1.04
    ï¸ı
    0.94
    ł
    0.93
    ×Ļ×
    0.92
    ãĥ¼ãĥ³
    0.91
    ा
    0.91
    750
    0.81
    ×Ļ
    0.79
    dating
    0.77
    ãĤĮ
    0.77
    Activations Density 0.008%

    No Known Activations