© 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. 8-RES-JB
    11. 3376
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical emergencies and treatments

    oai_token-act-pair · gpt-3.5-turbo

    references to medical emergencies and related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hilbert
    -0.52
     caveats
    -0.52
    anwhile
    -0.51
     quizz
    -0.51
     infancy
    -0.49
     archived
    -0.49
     nods
    -0.48
     notable
    -0.48
     unsurprisingly
    -0.47
    ãĤ´ãĥ³
    -0.47
    POSITIVE LOGITS
     ..."
    1.71
    ..."
    1.47
     âĢ¦"
    1.42
    âĢ¦"
    1.36
    âĢ¦."
    1.27
    ?"
    1.21
     [/
    1.20
     */
    1.19
    !!"
    1.18
    !"
    1.18
    Activations Density 1.584%

    No Known Activations