© 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. 9928
    Prev
    Next
    INDEX
    Explanations

    JavaScript key-value pairs with specific numerical values assigned

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and syntax-related elements in code or markup

    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
    tackle
    -0.65
    "/>
    -0.63
    "?
    -0.59
    ¶
    -0.56
    ¥ŀ
    -0.54
    ¥µ
    -0.54
    riger
    -0.54
     corrid
    -0.52
    "}],"
    -0.52
    !--
    -0.52
    POSITIVE LOGITS
     '
    2.83
     '[
    2.63
     '.
    2.44
     ',
    2.29
     '/
    2.10
     '(
    2.08
     ('
    1.90
     ['
    1.81
    .'
    1.80
    ,'
    1.77
    Activations Density 0.264%

    No Known Activations