© 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. 9-RES-JB
    11. 15433
    Prev
    Next
    INDEX
    Explanations

    ambiguous words or phrases that can be open to interpretation

    oai_token-act-pair · gpt-3.5-turbo

    negations and phrases indicating what should or should not happen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Corona
    -0.70
     Wid
    -0.70
     satisfactory
    -0.63
     restores
    -0.61
     Niet
    -0.60
     clears
    -0.60
     restoration
    -0.59
     Fug
    -0.59
     enhancements
    -0.59
     Xuan
    -0.57
    POSITIVE LOGITS
     be
    0.80
     underestimate
    0.80
     bother
    0.76
     underestimated
    0.75
     blindly
    0.75
     interfere
    0.75
    erest
    0.74
    oga
    0.74
    reated
    0.74
     hesitate
    0.73
    Activations Density 0.116%

    No Known Activations