© 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. 10-RES-JB
    11. 4486
    Prev
    Next
    INDEX
    Explanations

    words related to actions or descriptions of uncovering or revealing unknown or hidden information

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acious
    -0.65
     forgiven
    -0.63
     vectors
    -0.62
     selves
    -0.61
    selves
    -0.60
     differe
    -0.60
     Shed
    -0.59
     Egyptians
    -0.58
     gritty
    -0.58
     Brah
    -0.57
    POSITIVE LOGITS
    ffee
    1.50
    verage
    1.34
    xon
    1.33
    operative
    1.22
    operation
    1.20
    herent
    1.18
    aching
    1.15
    ff
    1.15
    pper
    1.12
    venant
    1.11
    Activations Density 0.024%

    No Known Activations