© 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. 10-RES-JB
    11. 4431
    Prev
    Next
    INDEX
    Explanations

    instances of the word "any"

    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
    izont
    -0.70
    gypt
    -0.66
    vier
    -0.64
    often
    -0.63
    uble
    -0.62
    rex
    -0.62
    cheon
    -0.61
    athe
    -0.60
    ip
    -0.59
    sometimes
    -0.58
    POSITIVE LOGITS
    THING
    1.29
     sort
    1.10
     particular
    1.05
     kind
    1.01
     semblance
    0.97
    thin
    0.94
     meaningful
    0.92
    ones
    0.91
    place
    0.88
     specific
    0.84
    Activations Density 0.072%

    No Known Activations