© 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. 2-RES-JB
    11. 9387
    Prev
    Next
    INDEX
    Explanations

    mentions of specific volumes in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to volumes of publications or series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riad
    -0.90
    otle
    -0.72
    hetics
    -0.68
    apolis
    -0.66
     Pearce
    -0.65
     Turing
    -0.64
    -|
    -0.63
    hetically
    -0.63
    roads
    -0.61
     Taiwanese
    -0.60
    POSITIVE LOGITS
    atility
    1.30
    atile
    1.23
    untary
    1.08
    umes
    1.05
    unte
    0.86
     juven
    0.83
    vol
    0.76
    VOL
    0.76
    edar
    0.76
    leys
    0.75
    Activations Density 0.010%

    No Known Activations