© 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. 8222
    Prev
    Next
    INDEX
    Explanations

    words related to victories or successful outcomes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "wins" in various contexts

    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
    Material
    -0.72
    ãĥĨ
    -0.67
    cgi
    -0.63
    izoph
    -0.61
    ilst
    -0.61
    Bul
    -0.60
    Parameter
    -0.60
    imaru
    -0.60
    ________________________________
    -0.59
    orm
    -0.59
    POSITIVE LOGITS
     wins
    3.64
     victories
    2.57
     win
    2.16
     defeats
    2.05
     Wins
    1.96
     victory
    1.74
     winning
    1.69
     successes
    1.64
     loses
    1.63
     winners
    1.60
    Activations Density 0.012%

    No Known Activations