© 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. 3222
    Prev
    Next
    INDEX
    Explanations

    mentions of specific picks in drafts

    oai_token-act-pair · gpt-3.5-turbo

    references to draft picks in sports

    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
    cers
    -0.85
    english
    -0.70
     tempor
    -0.69
    WARN
    -0.66
    blogs
    -0.66
    interrupted
    -0.64
    isf
    -0.63
    CTV
    -0.62
    uras
    -0.61
    selves
    -0.61
    POSITIVE LOGITS
     (#
    0.92
    pocket
    0.88
     picks
    0.84
     compens
    0.81
     Picks
    0.80
    ortment
    0.74
     pick
    0.74
     overall
    0.73
    picked
    0.71
    +.
    0.70
    Activations Density 0.029%

    No Known Activations