© 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. 6-RES-JB
    11. 3645
    Prev
    Next
    INDEX
    Explanations

    references to American football positions and player roles

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports team performance and player roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Panel
    -0.65
    xtap
    -0.63
     censored
    -0.60
     excerpt
    -0.60
     âĨij
    -0.59
     Recorded
    -0.58
     Feminist
    -0.58
     reviewer
    -0.58
    published
    -0.57
    txt
    -0.57
    POSITIVE LOGITS
     someday
    1.16
     offensively
    0.97
     coaching
    0.97
     rookie
    0.91
     anytime
    0.90
     playoff
    0.89
     postseason
    0.86
     defensively
    0.85
     offseason
    0.84
    omever
    0.83
    Activations Density 0.715%

    No Known Activations