© 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. 18786
    Prev
    Next
    INDEX
    Explanations

    keywords related to measurements or quantities

    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
    UTION
    -0.69
     Weaver
    -0.67
     Saunders
    -0.59
     Jackson
    -0.59
     Welch
    -0.57
    forge
    -0.56
    UTE
    -0.56
     disparate
    -0.56
    UME
    -0.56
    etta
    -0.56
    POSITIVE LOGITS
    abytes
    1.06
    rors
    1.02
    abyte
    1.00
    rible
    0.91
    anos
    0.86
    rib
    0.85
    gram
    0.80
    riers
    0.79
    rified
    0.79
    roid
    0.79
    Activations Density 0.021%

    No Known Activations