© 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. 0-RES-JB
    11. 16579
    Prev
    Next
    INDEX
    Explanations

    references to physical organs or medical conditions related to the heart

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the heart and cardiovascular health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    available
    -0.74
    idates
    -0.68
    soDeliveryDate
    -0.68
     Practices
    -0.67
     Unlimited
    -0.67
    --+
    -0.66
    ellar
    -0.66
    ional
    -0.66
    Anonymous
    -0.65
    gee
    -0.64
    POSITIVE LOGITS
     heart
    3.87
     hearts
    2.81
     Heart
    2.32
    Heart
    2.18
    heart
    2.14
     heartbeat
    1.95
     cardiac
    1.55
     Hearts
    1.48
     cardiovascular
    1.47
     soul
    1.45
    Activations Density 0.026%

    No Known Activations