© 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. 11-RES-JB
    11. 20627
    Prev
    Next
    INDEX
    Explanations

    references to the latest releases or updates

    oai_token-act-pair · gpt-3.5-turbo

    mentions of recent events or updates

    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
    then
    -0.99
    dinand
    -0.91
    ecause
    -0.83
    utical
    -0.82
    erved
    -0.81
    odan
    -0.80
    olin
    -0.78
    adow
    -0.78
    umenthal
    -0.77
    pload
    -0.75
    POSITIVE LOGITS
     incarnation
    1.36
     installment
    1.35
     iteration
    1.33
     edition
    1.16
     batch
    1.13
     twist
    1.08
     round
    1.04
     developments
    1.02
     setback
    0.98
     casualty
    0.96
    Activations Density 0.050%

    No Known Activations