Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 3212
    Prev
    Next
    INDEX
    Explanations

    medical emergency terms and terms related to programming functions and variables

    oai_token-act-pair · gpt-3.5-turbo

    urgent calls for action or attention in a crisis context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hend
    -0.82
     hemp
    -0.76
    anta
    -0.74
    л
    -0.73
    Ì
    -0.73
    anchez
    -0.72
    belt
    -0.71
    Ô
    -0.71
    melon
    -0.70
    orthy
    -0.69
    POSITIVE LOGITS
    call
    2.08
    Call
    2.08
     Call
    2.06
     call
    2.00
     Calls
    1.87
     CALL
    1.82
     caller
    1.78
     calls
    1.77
    calling
    1.68
     calling
    1.51
    Activations Density 0.247%

    No Known Activations