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. 22438
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations, especially related to health and safety concerns

    oai_token-act-pair · gpt-3.5-turbo

    mentions of locations and institutions related to educational or governmental settings

    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
    Newsletter
    -1.16
     ÂŃ
    -0.93
    etheless
    -0.92
     ¥
    -0.83
     underpin
    -0.82
     sufficiently
    -0.82
     epist
    -0.81
    itatively
    -0.81
     hitherto
    -0.79
     scarcely
    -0.79
    POSITIVE LOGITS
     FOX
    1.01
    FOX
    0.98
     COUNTY
    0.90
    Kids
    0.87
     homeowner
    0.87
    Owner
    0.85
    Copyright
    0.85
     Owner
    0.85
     crews
    0.84
     Neighbor
    0.83
    Activations Density 0.814%

    No Known Activations