© 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. 24554
    Prev
    Next
    INDEX
    Explanations

    phrases related to health risks and conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate various health risks

    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
    minus
    -0.90
    å°Ĩ
    -0.80
    books
    -0.77
     ILCS
    -0.77
    arta
    -0.75
    ãĤ¢ãĥ«
    -0.74
    cles
    -0.74
     istg
    -0.73
    iband
    -0.71
    hai
    -0.71
    POSITIVE LOGITS
     occurrence
    1.14
     miscarriage
    0.92
     infection
    0.88
     detection
    0.88
     relapse
    0.87
     suicide
    0.86
     adverse
    0.86
     encountering
    0.85
     harm
    0.84
     outcomes
    0.83
    Activations Density 0.131%

    No Known Activations