© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 2376
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to urgency or quick action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "AST," indicating a focus on parsing abstract syntax tree representations or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     persu
    -0.65
    mens
    -0.64
     compensation
    -0.64
     Disp
    -0.61
     disputes
    -0.61
     ple
    -0.61
     Deb
    -0.61
     theme
    -0.60
     Hy
    -0.59
     ev
    -0.59
    POSITIVE LOGITS
    AST
    4.23
    asts
    2.06
    aster
    1.76
    ast
    1.70
    asting
    1.68
    asted
    1.64
    asters
    1.61
    AS
    1.39
     AST
    1.33
    ANS
    1.33
    Activations Density 0.015%

    No Known Activations