© 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. 11-RES-JB
    11. 7079
    Prev
    Next
    INDEX
    Explanations

    dates and specific historical events

    oai_token-act-pair · gpt-3.5-turbo
    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
    adows
    -0.78
    Gameplay
    -0.69
     abound
    -0.66
     ¯
    -0.66
    nels
    -0.65
    values
    -0.65
    redients
    -0.65
    utics
    -0.65
    bats
    -0.64
    tics
    -0.64
    POSITIVE LOGITS
     foray
    1.31
     installment
    1.26
     outing
    1.17
     iteration
    1.09
     attempt
    1.06
     incarnation
    1.05
     hurdle
    1.00
     sighting
    0.97
     anniversary
    0.97
     episode
    0.96
    Activations Density 0.318%

    No Known Activations