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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7922
    Prev
    Next
    INDEX
    Explanations

    textual artifacts in the format of computer code

    oai_token-act-pair · gpt-3.5-turbo

    situations relating to health or food-related issues

    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
     Moff
    -0.74
    Dispatch
    -0.72
    ublic
    -0.72
     careers
    -0.71
    lisher
    -0.70
     ongoing
    -0.70
     Vanguard
    -0.69
    ilitation
    -0.68
    ventures
    -0.68
    iring
    -0.67
    POSITIVE LOGITS
     vinegar
    1.50
     feces
    1.47
     vomit
    1.47
     semen
    1.45
     grapes
    1.45
     mustard
    1.45
     urine
    1.43
     saliva
    1.41
     onions
    1.40
     jelly
    1.39
    Activations Density 0.556%

    No Known Activations