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. 9-RES-JB
    6. 22126
    Prev
    Next
    INDEX
    Explanations

    descriptions related to natural elements and physical surroundings

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical divisions and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interacted
    -0.91
    netflix
    -0.88
    ographics
    -0.88
    Downloadha
    -0.88
    inoa
    -0.88
    izzle
    -0.87
    ampunk
    -0.86
    CEO
    -0.84
    focused
    -0.84
    bang
    -0.84
    POSITIVE LOGITS
     pecul
    1.23
     splendid
    1.17
     solemn
    1.13
     pious
    1.12
     quarrel
    1.11
     heavenly
    1.11
     appell
    1.09
     precept
    1.09
     wretched
    1.07
    ught
    1.06
    Activations Density 0.707%

    No Known Activations