© 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. 10-RES-JB
    11. 10121
    Prev
    Next
    INDEX
    Explanations

    comma-separated phrases

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases or clauses indicating agreement or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -+
    -0.75
    igion
    -0.74
    arted
    -0.73
    èĢħ
    -0.71
    ende
    -0.70
    foreseen
    -0.69
    ighed
    -0.69
    minster
    -0.69
    folio
    -0.68
    mination
    -0.68
    POSITIVE LOGITS
     yes
    1.10
     sir
    1.07
     indeed
    1.03
     yeah
    1.02
     there
    0.98
     THERE
    0.91
     technically
    0.90
     it
    0.90
     please
    0.88
     seriously
    0.86
    Activations Density 0.050%

    No Known Activations