© 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. 16593
    Prev
    Next
    INDEX
    Explanations

    dates written in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses and related punctuation

    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
     erosion
    -0.72
     prey
    -0.71
     generation
    -0.71
     clin
    -0.70
     stigmat
    -0.70
     intangible
    -0.69
     intensive
    -0.69
     gradual
    -0.67
     everyday
    -0.67
     drift
    -0.67
    POSITIVE LOGITS
    PDF
    1.65
    pdf
    1.53
    emphasis
    1.47
    pictured
    1.46
    see
    1.37
    below
    1.35
    again
    1.31
    above
    1.30
    via
    1.30
    July
    1.28
    Activations Density 0.138%

    No Known Activations