© 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. 11-RES-JB
    11. 24184
    Prev
    Next
    INDEX
    Explanations

    references to publications or sources within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of opening parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prey
    -0.83
     incons
    -0.76
     inward
    -0.76
     hydrogen
    -0.73
     lag
    -0.72
     clin
    -0.72
     stem
    -0.71
     pale
    -0.71
     generation
    -0.70
     synt
    -0.70
    POSITIVE LOGITS
    which
    1.79
    pictured
    1.77
    formerly
    1.75
    although
    1.62
    whose
    1.62
    now
    1.62
    see
    1.61
    later
    1.59
    among
    1.57
    PDF
    1.56
    Activations Density 0.150%

    No Known Activations