© 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. 4790
    Prev
    Next
    INDEX
    Explanations

    references to events or actions related to a specific draft, potentially in the context of sports or legislation

    oai_token-act-pair · gpt-3.5-turbo

    references to the NFL draft

    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
    umers
    -0.76
    acea
    -0.74
    AppData
    -0.72
    idia
    -0.71
    lang
    -0.69
    elli
    -0.67
    areth
    -0.66
    alus
    -0.66
    oola
    -0.66
    orus
    -0.65
    POSITIVE LOGITS
     draft
    3.88
     drafts
    3.08
     Draft
    2.98
    draft
    2.81
    Draft
    2.61
     drafting
    2.31
     drafted
    2.19
     dra
    1.92
    RAFT
    1.35
     scouting
    1.22
    Activations Density 0.013%

    No Known Activations