© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3532
    Prev
    Next
    INDEX
    Explanations

    information related to sports drafts, player evaluations, and team decisions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    variations of the verb "to be" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zsche
    -0.81
    arta
    -0.81
    sth
    -0.80
    hoe
    -0.76
    anguages
    -0.74
    idth
    -0.73
    Panel
    -0.72
    resist
    -0.72
    pmwiki
    -0.71
    ogyn
    -0.71
    POSITIVE LOGITS
     traded
    1.09
     healthy
    1.07
     drafted
    1.01
     eligible
    0.95
     available
    0.90
     sidelined
    0.88
     ready
    0.87
     ben
    0.87
     signed
    0.86
     utilized
    0.85
    Activations Density 0.186%

    No Known Activations