© 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. 11-RES-JB
    11. 13671
    Prev
    Next
    INDEX
    Explanations

    indicators of enumeration or listing, such as "Another" before a list item

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence of multiple perspectives or considerations

    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
    endas
    -0.80
    bows
    -0.79
    ornings
    -0.78
    ÃįÃį
    -0.76
    ences
    -0.76
    ouls
    -0.75
    hips
    -0.75
    anism
    -0.75
    olas
    -0.74
    ravings
    -0.72
    POSITIVE LOGITS
     complication
    1.22
     factor
    1.18
     possibility
    1.17
     drawback
    1.16
     example
    1.15
     aspect
    1.14
     reason
    1.13
     notable
    1.09
     option
    1.07
     noteworthy
    1.07
    Activations Density 0.108%

    No Known Activations