© 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. 7-RES-JB
    11. 1854
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams or players

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms and references related to sports teams or players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osponsors
    -0.81
    ording
    -0.80
    atel
    -0.76
    ertodd
    -0.75
    ozy
    -0.75
    ento
    -0.75
    urring
    -0.73
    ude
    -0.69
    udes
    -0.68
    paren
    -0.68
    POSITIVE LOGITS
     midfield
    1.05
     playoff
    1.00
     preseason
    0.99
     undefeated
    0.99
     own
    0.97
     unbeaten
    0.96
     goalkeeper
    0.93
     halftime
    0.93
     defensive
    0.93
     keeper
    0.92
    Activations Density 0.132%

    No Known Activations