© 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. 20877
    Prev
    Next
    INDEX
    Explanations

    specific numerical values related to statistics or measurements

    oai_token-act-pair · gpt-3.5-turbo

    quantitative statistics related to sports performance

    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
    igm
    -0.70
    ricia
    -0.65
    phant
    -0.64
    zos
    -0.64
     summar
    -0.63
     Keynes
    -0.63
     Patriarch
    -0.62
    bill
    -0.62
     Pill
    -0.61
    netflix
    -0.61
    POSITIVE LOGITS
     mph
    0.97
    %,
    0.90
     seconds
    0.87
    %
    0.87
     stitches
    0.86
     minutes
    0.85
     possessions
    0.85
     FANTASY
    0.84
     percent
    0.83
    mph
    0.83
    Activations Density 0.138%

    No Known Activations