© 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. 18472
    Prev
    Next
    INDEX
    Explanations

    numbers related to quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    quantifiable statistics or numerical data

    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
    Ranked
    -0.61
    slow
    -0.58
     circa
    -0.58
     Prophet
    -0.57
    rade
    -0.57
    Agent
    -0.57
    ROR
    -0.56
    inges
    -0.56
     Barron
    -0.56
     Resurrection
    -0.56
    POSITIVE LOGITS
    %"
    1.16
    %
    1.11
     percent
    1.09
    %:
    0.98
    %.
    0.95
     thousand
    0.95
     000
    0.95
    %;
    0.93
     million
    0.92
    %,
    0.83
    Activations Density 0.125%

    No Known Activations