© 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. 9-RES-JB
    11. 13197
    Prev
    Next
    INDEX
    Explanations

    keywords related to various industries and technologies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    `.
    -0.66
    `,
    -0.65
     Helpful
    -0.60
     ..........
    -0.59
    ãĤ¡
    -0.58
    !.
    -0.58
    Ò
    -0.58
    ;;
    -0.58
    borgh
    -0.57
    \",
    -0.57
    POSITIVE LOGITS
     hasn
    0.95
     isn
    0.94
     disappears
    0.92
     portion
    0.89
     tends
    0.89
     wasn
    0.88
     doesn
    0.84
     lacks
    0.83
     becomes
    0.81
     aspect
    0.81
    Activations Density 0.970%

    No Known Activations