© 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. 21798
    Prev
    Next
    INDEX
    Explanations

    dates and sequences of events

    oai_token-act-pair · gpt-3.5-turbo

    references to recent events or conditions related to liberation and displacement

    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
     compliments
    -0.73
     differential
    -0.67
     affirmative
    -0.66
     GOODMAN
    -0.65
     compliment
    -0.65
     partName
    -0.63
     endorsing
    -0.62
     pairing
    -0.62
     quoting
    -0.61
     ital
    -0.61
    POSITIVE LOGITS
    destroy
    1.06
    pleted
    1.02
    built
    1.00
    Built
    0.93
    ached
    0.92
    uilding
    0.91
    forest
    0.90
    build
    0.88
    occupied
    0.86
    ories
    0.85
    Activations Density 0.455%

    No Known Activations