© 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. 7-RES-JB
    11. 21477
    Prev
    Next
    INDEX
    Explanations

    medical terms related to cardiovascular health

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cardiovascular health and associated risk factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    houses
    -0.90
    onomy
    -0.84
    arthed
    -0.83
    DAQ
    -0.79
    STER
    -0.79
    cham
    -0.79
    lee
    -0.76
    lem
    -0.76
    house
    -0.76
    gradation
    -0.75
    POSITIVE LOGITS
    obal
    0.84
    xual
    0.78
    omez
    0.76
     bis
    0.71
     Sins
    0.68
     Sakuya
    0.67
     Ramos
    0.66
    rious
    0.66
     hypertension
    0.66
    ously
    0.66
    Activations Density 0.127%

    No Known Activations