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. 7-RES-JB
    6. 10231
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names, potentially including surnames or full names

    oai_token-act-pair · gpt-3.5-turbo

    names or terms associated with uniqueness or specific identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iated
    -0.95
    seys
    -0.94
    isphere
    -0.93
    iating
    -0.93
    iations
    -0.88
    owment
    -0.87
    odd
    -0.87
    itability
    -0.86
    oran
    -0.85
    anmar
    -0.85
    POSITIVE LOGITS
     Bou
    0.96
     Royale
    0.94
     Hollande
    0.93
     franc
    0.89
     Franc
    0.89
     Nou
    0.88
     Blanc
    0.88
     Ãł
    0.84
     Vie
    0.83
     du
    0.83
    Activations Density 0.102%

    No Known Activations