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. 4-RES-JB
    6. 13007
    Prev
    Next
    INDEX
    Explanations

    adjectives describing unsettling or disturbing characteristics

    oai_token-act-pair · gpt-3.5-turbo

    words that describe something as creepy or associated with creepiness

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

    No Comments

    Negative Logits
    shire
    -0.92
    ership
    -0.86
    inen
    -0.86
    mental
    -0.85
    ribut
    -0.82
    aire
    -0.80
    hip
    -0.80
    lete
    -0.80
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.80
    iche
    -0.78
    POSITIVE LOGITS
     stuff
    0.84
     sounding
    0.79
     fun
    0.78
     looking
    0.76
     shit
    0.76
     tid
    0.75
     Guys
    0.74
     enough
    0.74
     darn
    0.74
     little
    0.73
    Activations Density 0.040%

    No Known Activations