© 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. 8-RES-JB
    11. 956
    Prev
    Next
    INDEX
    Explanations

    information about notable individuals, events, and announcements

    oai_token-act-pair · gpt-3.5-turbo

    references to awards and accolades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tended
    -0.87
     wob
    -0.77
     pse
    -0.73
     cumbers
    -0.71
    addafi
    -0.71
    estate
    -0.70
     botched
    -0.69
    otom
    -0.69
     nerv
    -0.68
     WATCHED
    -0.68
    POSITIVE LOGITS
     2019
    0.99
    2018
    0.96
     2018
    0.93
    exclusive
    0.85
     2021
    0.83
     upcoming
    0.82
     2017
    0.80
    Series
    0.79
     partnership
    0.78
    2019
    0.78
    Activations Density 0.835%

    No Known Activations