© 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. 15646
    Prev
    Next
    INDEX
    Explanations

    connections to defects or deficiencies in physical objects or medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to deficiencies and defects, particularly in a nutritional context

    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
    laus
    -0.80
    mares
    -0.71
    ctors
    -0.71
    pper
    -0.71
    isSpecialOrderable
    -0.70
    İ
    -0.70
    zai
    -0.70
    ometric
    -0.69
    kers
    -0.69
    skirts
    -0.69
    POSITIVE LOGITS
     deficiency
    1.18
     deficient
    1.07
    iencies
    1.05
     deficiencies
    1.03
    icient
    0.87
     faulty
    0.80
     defective
    0.79
     defects
    0.76
     Errors
    0.73
    encies
    0.73
    Activations Density 0.021%

    No Known Activations