© 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. 11-RES-JB
    11. 18662
    Prev
    Next
    INDEX
    Explanations

    sports-related terms like player names and team names

    oai_token-act-pair · gpt-3.5-turbo

    references to sports statistics and player information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     psychiat
    -0.70
     plur
    -0.69
     reconc
    -0.68
    leanor
    -0.67
    uana
    -0.66
     subsequ
    -0.66
     disg
    -0.65
     behavi
    -0.64
    pecially
    -0.62
     therap
    -0.62
    POSITIVE LOGITS
     Age
    1.00
    advertising
    0.97
    Age
    0.91
    Height
    0.88
     LSU
    0.88
     PIT
    0.87
    Constructed
    0.87
     PHI
    0.86
    Draft
    0.85
     Clemson
    0.84
    Activations Density 0.142%

    No Known Activations