© 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. 6-RES-JB
    11. 13720
    Prev
    Next
    INDEX
    Explanations

    mentions related to sickness or illness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of illness or dissatisfaction, particularly in a colloquial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unlaw
    -0.75
     compr
    -0.66
     Unch
    -0.66
    wcsstore
    -0.66
    adr
    -0.64
    ETHOD
    -0.63
     sanctioned
    -0.60
    merce
    -0.60
     rul
    -0.60
     Hier
    -0.59
    POSITIVE LOGITS
    ening
    1.29
    ened
    1.18
    bay
    1.16
    nesses
    0.96
    ly
    0.93
    est
    0.89
    ert
    0.88
    etts
    0.86
    le
    0.85
    ness
    0.85
    Activations Density 0.019%

    No Known Activations