© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 6981
    Prev
    Next
    INDEX
    Explanations

    severe medical conditions and injuries

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating serious medical conditions or injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pire
    -0.80
    pires
    -0.79
    xxxxxxxx
    -0.79
    pired
    -0.79
    amera
    -0.79
    kers
    -0.76
    enaries
    -0.76
    AUT
    -0.75
    olicited
    -0.73
    rium
    -0.73
    POSITIVE LOGITS
     consequences
    1.11
     shortage
    1.06
     impairment
    1.03
     injury
    1.03
     allergic
    1.02
     illness
    1.02
     deterioration
    1.01
     disabilities
    1.00
     malnutrition
    0.99
     repercussions
    0.98
    Activations Density 0.046%

    No Known Activations