© 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. 2666
    Prev
    Next
    INDEX
    Explanations

    statistics or numbers

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and their associated quantities or percentages

    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
    multipl
    -0.78
    yrinth
    -0.74
    lay
    -0.73
    especially
    -0.71
    loo
    -0.69
     indo
    -0.68
    ramid
    -0.67
    raught
    -0.67
    multiple
    -0.66
    alle
    -0.66
    POSITIVE LOGITS
     percent
    1.01
     cents
    0.96
    %
    0.86
    %.
    0.84
     weeks
    0.79
     hours
    0.79
     minutes
    0.77
    %,
    0.75
     seconds
    0.73
     fraction
    0.70
    Activations Density 0.172%

    No Known Activations