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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 5739
    Prev
    Next
    INDEX
    Explanations

    phrases related to a competitive ranking or leaderboard, potentially in a gaming context

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and references to steps or sections in a structured sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hist
    -0.78
    Dial
    -0.77
    cele
    -0.73
     paran
    -0.72
    comed
    -0.72
    phot
    -0.71
    paralle
    -0.70
    accompan
    -0.70
    absor
    -0.70
    itiz
    -0.69
    POSITIVE LOGITS
     ½
    0.82
     II
    0.80
     2
    0.80
     XI
    0.79
     3
    0.74
     VII
    0.74
     Nine
    0.73
     11
    0.72
     10
    0.72
     Two
    0.71
    Activations Density 0.081%

    No Known Activations