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. 8-RES-JB
    6. 9608
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contact or interaction with others

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "getting in" or variations thereof

    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
     brim
    -0.57
    ALD
    -0.57
     EMP
    -0.55
     silhou
    -0.53
     Bullets
    -0.53
     pall
    -0.53
     Scand
    -0.52
    =]
    -0.52
    cia
    -0.52
     husbands
    -0.51
    POSITIVE LOGITS
    ordinate
    0.97
    offensive
    0.93
    touch
    0.88
    byss
    0.85
    roads
    0.83
    bred
    0.82
    ked
    0.81
    hibited
    0.80
    Touch
    0.79
    utters
    0.79
    Activations Density 0.055%

    No Known Activations