© 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. 9-RES-JB
    11. 4206
    Prev
    Next
    INDEX
    Explanations

    locations or objects hidden under or beneath something

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERG
    -0.77
    eln
    -0.69
    och
    -0.69
    QL
    -0.65
    yah
    -0.64
    DN
    -0.62
    izu
    -0.61
    okin
    -0.61
    ãĥ£
    -0.61
    Ê
    -0.59
    POSITIVE LOGITS
    neath
    1.26
     layers
    1.04
    sea
    1.03
    pants
    1.03
    coat
    1.00
    brush
    0.97
    growth
    0.94
     coats
    0.89
     bushes
    0.88
     blankets
    0.88
    Activations Density 0.075%

    No Known Activations