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. 22372
    Prev
    Next
    INDEX
    Explanations

    **phrases containing the word "wanted" or variations of it**

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'w'

    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
     reservations
    -0.70
     inhibition
    -0.66
    ï¸ı
    -0.63
    gow
    -0.61
     responders
    -0.61
     plaintiff
    -0.61
    ŃĶ
    -0.61
     corps
    -0.60
     Aram
    -0.60
     latitude
    -0.59
    POSITIVE LOGITS
    elcome
    1.52
    isdom
    1.51
    itness
    1.47
    orship
    1.44
    onder
    1.43
    ield
    1.39
    oven
    1.38
    earing
    1.38
    orry
    1.36
    ielding
    1.35
    Activations Density 0.026%

    No Known Activations