© 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. 4-RES-JB
    11. 2153
    Prev
    Next
    INDEX
    Explanations

    dates in comma-separated format

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and specific numerical references

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

    No Comments

    Negative Logits
     domest
    -0.64
    ahu
    -0.63
    edIn
    -0.58
     scratched
    -0.57
    arkin
    -0.56
     medieval
    -0.56
    wagen
    -0.55
     sprang
    -0.55
    iami
    -0.55
     monop
    -0.54
    POSITIVE LOGITS
     RELEASE
    0.86
     IST
    0.85
    quickShipAvailable
    0.85
     PDT
    0.82
     REUTERS
    0.79
     partName
    0.78
     Retrieved
    0.77
     PST
    0.73
     UTC
    0.70
     Authorization
    0.70
    Activations Density 0.229%

    No Known Activations