© 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. 7692
    Prev
    Next
    INDEX
    Explanations

    detailed information or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to details or specifics of various topics or events

    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
    asus
    -0.86
    rade
    -0.72
    ammers
    -0.72
    ratulations
    -0.70
    boa
    -0.68
    sw
    -0.67
    ÃŃs
    -0.67
    igham
    -0.65
    vic
    -0.65
    mire
    -0.64
    POSITIVE LOGITS
     redacted
    1.04
     surrounding
    0.97
     details
    0.97
     glean
    0.94
     detail
    0.90
     thereof
    0.87
    displayText
    0.87
     pertaining
    0.84
    paces
    0.84
     regarding
    0.82
    Activations Density 0.050%

    No Known Activations