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. 12836
    Prev
    Next
    INDEX
    Explanations

    terms related to gaming, attributes, and instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to fictional characters or elements in storytelling

    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
     withd
    -0.93
    theless
    -0.87
     conclud
    -0.85
     compr
    -0.81
     confir
    -0.78
     psychiat
    -0.77
     electing
    -0.75
     accomp
    -0.73
     toget
    -0.73
     includ
    -0.72
    POSITIVE LOGITS
     Profile
    0.87
     Decay
    0.86
     Drops
    0.84
     Warp
    0.82
     Whip
    0.82
     Ratio
    0.81
     Frog
    0.80
     Sword
    0.79
     Sexy
    0.79
     Clone
    0.79
    Activations Density 0.578%

    No Known Activations