© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 20957
    Prev
    Next
    INDEX
    Explanations

    release dates

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding the existence or status of various entertainment-related entities or events

    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
    inventoryQuantity
    -0.82
    isms
    -0.80
    ousands
    -0.76
    errors
    -0.76
    fire
    -0.71
    indu
    -0.71
    ality
    -0.67
     Cosponsors
    -0.66
    iphany
    -0.64
    failed
    -0.63
    POSITIVE LOGITS
     slated
    1.34
     scheduled
    1.13
     narrated
    1.02
     currently
    1.01
     available
    1.01
     priced
    0.99
     expected
    0.95
     billed
    0.94
     coming
    0.93
     shaping
    0.93
    Activations Density 0.175%

    No Known Activations