© 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. 4829
    Prev
    Next
    INDEX
    Explanations

    general categories or lists of items

    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
     robbers
    -0.68
     fart
    -0.63
    poke
    -0.60
     prin
    -0.56
    CLOSE
    -0.56
    LOAD
    -0.55
    proof
    -0.54
     trespass
    -0.54
     indictment
    -0.53
     blink
    -0.53
    POSITIVE LOGITS
    .,
    1.73
    eter
    1.61
    .;
    1.58
    .?
    1.58
    .).
    1.47
    .:
    1.44
    .),
    1.41
    .—
    1.34
    .,"
    1.31
    etc
    1.26
    Activations Density 0.020%

    No Known Activations