© 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. 1-RES-JB
    11. 20327
    Prev
    Next
    INDEX
    Explanations

    phrases related to mistakes or accidents

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with incidents, errors, and mishaps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ESA
    -0.72
     frustration
    -0.69
     distraction
    -0.61
     commencement
    -0.60
     delinqu
    -0.59
    EngineDebug
    -0.58
     Feder
    -0.57
     bed
    -0.57
    Effective
    -0.57
     renewal
    -0.57
    POSITIVE LOGITS
    hops
    1.23
    mith
    1.15
    hips
    1.10
    peak
    1.08
    hare
    1.08
    uggest
    1.04
    hooting
    1.00
    ouls
    0.98
    ĸļ
    0.97
    poons
    0.97
    Activations Density 0.173%

    No Known Activations