© 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. 4-RES-JB
    11. 10125
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Win" followed by numbers that could potentially represent versions or models

    oai_token-act-pair · gpt-3.5-turbo

    references to "Win" in various contexts

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

    No Comments

    Negative Logits
    âĶģ
    -0.77
    ADRA
    -0.75
    £ı
    -0.71
     condu
    -0.70
     trave
    -0.70
    ĸļ
    -0.68
     destro
    -0.68
     gravity
    -0.68
    ¿½
    -0.67
    ħĭ
    -0.67
    POSITIVE LOGITS
    ners
    1.16
    frey
    1.06
    nings
    0.99
    throp
    0.95
    fred
    0.94
    win
    0.94
    ning
    0.91
    NER
    0.86
    now
    0.83
    ces
    0.82
    Activations Density 0.012%

    No Known Activations