© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9861
    Prev
    Next
    INDEX
    Explanations

    dates and specific time references

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time periods or significant events

    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
     strict
    -0.62
    iterator
    -0.60
     jurisd
    -0.60
     pric
    -0.57
     cryst
    -0.56
     IOC
    -0.56
    charge
    -0.55
     receipt
    -0.52
     stricter
    -0.52
     reuse
    -0.51
    POSITIVE LOGITS
     viz
    1.01
     regarding
    0.93
     namely
    0.89
    days
    0.87
     concerning
    0.87
     onwards
    0.84
    isSpecialOrderable
    0.78
    acly
    0.77
    -'
    0.77
    _.
    0.74
    Activations Density 0.311%

    No Known Activations