© 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. 11-RES-JB
    11. 16652
    Prev
    Next
    INDEX
    Explanations

    conjunctions or transition phrases indicating a contrast or exception

    oai_token-act-pair · gpt-3.5-turbo

    transition phrases that indicate contrast or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pione
    -0.78
    eatured
    -0.74
    umbn
    -0.73
    apult
    -0.71
    usalem
    -0.69
    tyard
    -0.68
    yssey
    -0.68
    ilic
    -0.67
    insula
    -0.67
    espie
    -0.67
    POSITIVE LOGITS
    .
    1.45
    .(
    1.28
    .[
    1.24
    .-
    1.20
    .–
    1.18
    !.
    1.16
    .]
    1.14
    .:
    1.13
    .</
    1.11
    .<
    1.10
    Activations Density 0.330%

    No Known Activations