© 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. 8-RES-JB
    11. 3273
    Prev
    Next
    INDEX
    Explanations

    first occurrences or instances of events or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to significant or historic first occurrences

    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
    riber
    -0.68
    sleep
    -0.68
    each
    -0.67
    plays
    -0.67
    ractor
    -0.67
    Ïī
    -0.64
    lag
    -0.64
    obby
    -0.64
    tics
    -0.63
    aths
    -0.63
    POSITIVE LOGITS
     foray
    1.05
     installment
    1.03
     thing
    0.97
     casualty
    0.97
     baseman
    0.96
     ever
    0.93
     responders
    0.92
     glimpse
    0.87
     indication
    0.86
     step
    0.83
    Activations Density 0.070%

    No Known Activations