© 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. 8-RES-JB
    11. 10376
    Prev
    Next
    INDEX
    Explanations

    number ranges formatted as "number-number"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time periods or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rica
    -0.78
     Borders
    -0.75
     Clyde
    -0.74
     Lanka
    -0.70
     RPGs
    -0.70
     heights
    -0.69
     Thumbnails
    -0.67
     Athe
    -0.66
     Scouts
    -0.65
     charms
    -0.65
    POSITIVE LOGITS
    hour
    1.31
    year
    1.29
    minute
    1.25
    million
    1.23
    month
    1.23
    degree
    1.19
    issue
    1.18
    mile
    1.17
    member
    1.14
    kil
    1.12
    Activations Density 0.131%

    No Known Activations