© 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. 21504
    Prev
    Next
    INDEX
    Explanations

    examples of specific scenarios or actions related to rules or guidelines

    oai_token-act-pair · gpt-3.5-turbo

    instances and examples of "such as" or "like" to introduce clarifications or lists

    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
    SPONSORED
    -1.02
    Scroll
    -0.87
    ibilities
    -0.78
    edom
    -0.73
    sylvania
    -0.72
    vant
    -0.71
    Sources
    -0.70
    ynes
    -0.70
    thal
    -0.70
    Nine
    -0.68
    POSITIVE LOGITS
     removing
    0.97
     avoiding
    0.94
     selecting
    0.92
     deleting
    0.90
     preventing
    0.90
     reducing
    0.88
     needing
    0.87
     cance
    0.86
     correcting
    0.86
     creating
    0.85
    Activations Density 0.182%

    No Known Activations