© 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. 11-RES-JB
    11. 20423
    Prev
    Next
    INDEX
    Explanations

    mentions of political party affiliations and governmental positions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of commas in discussions related to political figures or groups

    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
    ield
    -0.71
    =#
    -0.68
    dule
    -0.67
    «ĺ
    -0.67
    Merit
    -0.66
    ģĸ
    -0.65
    PORT
    -0.64
    miss
    -0.61
     Theft
    -0.61
    advertisement
    -0.60
    POSITIVE LOGITS
     including
    1.27
    including
    1.05
     meanwhile
    1.01
     accustomed
    0.99
     fearing
    0.96
     rejoice
    0.96
     notably
    0.95
     aided
    0.93
     sensing
    0.92
     especially
    0.91
    Activations Density 0.163%

    No Known Activations