© 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. 10-RES-JB
    11. 10044
    Prev
    Next
    INDEX
    Explanations

    mentions of winning or success

    oai_token-act-pair · gpt-3.5-turbo

    references to success or failure in competitive contexts

    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
    âĶģ
    -0.73
    VILLE
    -0.72
    SEE
    -0.70
    aryn
    -0.67
    haar
    -0.65
    anium
    -0.65
    redits
    -0.64
    opian
    -0.63
    alam
    -0.62
    ratom
    -0.62
    POSITIVE LOGITS
     streak
    1.32
    est
    1.08
     bidder
    1.05
     streaks
    1.00
     formula
    0.88
     combination
    0.85
     combinations
    0.79
     bid
    0.79
     ticket
    0.78
     percentage
    0.78
    Activations Density 0.032%

    No Known Activations