© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5361
    Prev
    Next
    INDEX
    Explanations

    concepts related to measurement, evaluation, and assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to reasoning and argumentation

    oai_token-act-pair · gpt-3.5-turbo
    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
    !.
    -0.87
    .:
    -0.82
    `.
    -0.79
    '.
    -0.77
    ';
    -0.71
    .).
    -0.70
    %.
    -0.70
    +.
    -0.70
    ().
    -0.69
    ,...
    -0.67
    POSITIVE LOGITS
    pires
    0.73
     entails
    0.64
     intrinsically
    0.61
     outweigh
    0.61
     constitutes
    0.61
     involves
    0.58
     equals
    0.56
     physical
    0.56
     harms
    0.56
     perceived
    0.55
    Activations Density 1.269%

    No Known Activations