© 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. 6-RES-JB
    11. 17725
    Prev
    Next
    INDEX
    Explanations

    quotes from different people

    oai_token-act-pair · gpt-3.5-turbo

    dialogue and quotes in the text

    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
    cffffcc
    -0.78
    pes
    -0.77
    qqa
    -0.76
    invoke
    -0.75
    scan
    -0.75
    folios
    -0.74
    emin
    -0.72
    ebin
    -0.69
    oin
    -0.68
    pend
    -0.68
    POSITIVE LOGITS
     teammate
    1.02
    NBA
    0.98
     coach
    0.96
     Packers
    0.94
     ESPN
    0.91
     rookies
    0.91
     NFL
    0.90
     coaches
    0.90
    ESPN
    0.89
     teammates
    0.89
    Activations Density 0.175%

    No Known Activations