© 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. 9-RES-JB
    11. 4641
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political figures or organizations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of empty or non-informative content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Andersen
    -0.62
    example
    -0.58
    ener
    -0.56
    schild
    -0.56
    Ïī
    -0.56
     Lone
    -0.55
     Siber
    -0.55
     bec
    -0.55
    phy
    -0.55
    blers
    -0.54
    POSITIVE LOGITS
     lawmakers
    0.83
     lawmaker
    0.81
     BJP
    0.80
     deputy
    0.79
     officials
    0.77
     Secretary
    0.77
     approves
    0.76
     secretary
    0.74
     Says
    0.74
     accuses
    0.74
    Activations Density 0.340%

    No Known Activations