© 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. 572
    Prev
    Next
    INDEX
    Explanations

    adjective-noun pairs

    oai_token-act-pair · gpt-3.5-turbo

    prepositional phrases that indicate relationships or actions involving submission or commentary

    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
     darn
    -0.79
    $.
    -0.74
    usercontent
    -0.67
     realised
    -0.67
    acci
    -0.64
     realistically
    -0.64
    gage
    -0.64
    .(
    -0.63
    *.
    -0.63
    ptin
    -0.63
    POSITIVE LOGITS
     behalf
    0.69
     Fired
    0.69
     Collider
    0.64
     archived
    0.62
     Register
    0.62
    tained
    0.61
    ©¶æ
    0.60
     Ars
    0.60
     Melody
    0.60
     Sent
    0.59
    Activations Density 0.337%

    No Known Activations