© 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. 8-RES-JB
    11. 17767
    Prev
    Next
    INDEX
    Explanations

    positions and roles in American football, such as safety, running back, tight end, linebacker, quarterback, guard, and tackle

    oai_token-act-pair · gpt-3.5-turbo

    football positions and roles

    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
    ombat
    -0.93
    sth
    -0.73
    pload
    -0.70
    urat
    -0.67
     destruct
    -0.67
    heit
    -0.65
     Agenda
    -0.65
    rawdownloadcloneembedreportprint
    -0.62
    izoph
    -0.60
    KING
    -0.59
    POSITIVE LOGITS
     extraord
    0.93
     coach
    0.89
     tandem
    0.85
    /.
    0.83
     duo
    0.80
     corps
    0.80
     coaches
    0.75
     drafted
    0.75
     talent
    0.73
     Reggie
    0.73
    Activations Density 0.119%

    No Known Activations