© 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. 8-RES-JB
    11. 3986
    Prev
    Next
    INDEX
    Explanations

    words related to sports coaching positions

    oai_token-act-pair · gpt-3.5-turbo

    references to coaching positions and individuals involved in football coaching

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bridge
    -0.86
    ered
    -0.78
     Brah
    -0.73
    uras
    -0.71
    hands
    -0.67
    hire
    -0.65
    opian
    -0.65
    kid
    -0.64
    eed
    -0.63
    ering
    -0.62
    POSITIVE LOGITS
    acies
    0.82
    ãĥ£
    0.78
    ennes
    0.74
    ACY
    0.73
    Äĩ
    0.68
    ossession
    0.67
    rone
    0.66
    UTH
    0.66
    acy
    0.65
    ITIES
    0.64
    Activations Density 0.096%

    No Known Activations