© 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. 10-RES-JB
    11. 4380
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a specific point or turning moment in a text or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce significant points or concepts, particularly those starting with "where."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    978
    -0.66
    advertisement
    -0.65
    dayName
    -0.64
     incent
    -0.63
    ãĥīãĥ©
    -0.61
    ãĥ´
    -0.60
    775
    -0.60
    asts
    -0.60
     annually
    -0.60
    ãģ®å®
    -0.59
    POSITIVE LOGITS
     things
    1.19
     we
    0.76
     you
    0.74
     Obi
    0.74
     tragedies
    0.72
     tragedy
    0.70
     tensions
    0.69
     everything
    0.69
     trouble
    0.66
     Things
    0.66
    Activations Density 0.098%

    No Known Activations