© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3463
    Prev
    Next
    INDEX
    Explanations

    statistics and descriptions related to basketball player performance, particularly in terms of shooting percentages and ratings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    numerical statistics related to performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    æ©
    -0.67
    ě
    -0.66
    ę
    -0.65
    Ě
    -0.65
    û
    -0.65
    Ĝ
    -0.65
    Ē
    -0.65
    ĕ
    -0.65
    embedreportprint
    -0.65
    ÷
    -0.65
    POSITIVE LOGITS
     .
    1.09
     minus
    0.94
     +
    0.89
     -
    0.82
    -.
    0.81
     91
    0.77
     ±
    0.76
     âĪĴ
    0.74
     94
    0.74
    +.
    0.73
    Activations Density 0.190%

    No Known Activations