© 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. 4217
    Prev
    Next
    INDEX
    Explanations

    references to the location "Ha"

    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
    âķIJ
    -0.79
    ments
    -0.75
    mented
    -0.73
    eenth
    -0.72
     multiplier
    -0.72
    ij士
    -0.69
    é¾įå¥ij士
    -0.67
    manship
    -0.65
    eers
    -0.61
    parts
    -0.59
    POSITIVE LOGITS
    irst
    1.19
    vel
    1.09
    ifa
    1.08
    aretz
    1.07
    iley
    1.04
    verty
    1.03
    iku
    1.03
    pless
    1.02
    Ha
    0.96
    ilee
    0.95
    Activations Density 0.010%

    No Known Activations