© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 7298
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrasts or exceptions

    oai_token-act-pair · gpt-3.5-turbo

    the use of words indicating exceptions or negations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ..."
    -0.98
    "],"
    -0.69
     ..
    -0.66
     etc
    -0.65
     ""
    -0.65
    .","
    -0.65
     ....
    -0.63
     ...
    -0.63
     �
    -0.63
     orbs
    -0.63
    POSITIVE LOGITS
    odore
    1.11
    xiety
    1.08
    resa
    1.06
    withstanding
    0.92
    hibit
    0.89
    alyst
    0.87
    aminer
    0.80
     Facts
    0.80
    achusetts
    0.79
    ories
    0.79
    Activations Density 0.551%

    No Known Activations