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. 411
    Prev
    Next
    INDEX
    Explanations

    references to locations in the United States

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and statistics within the United States

    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
    errors
    -0.68
     captains
    -0.65
    struct
    -0.65
    iosyn
    -0.65
    Det
    -0.63
    PsyNetMessage
    -0.62
     councillors
    -0.61
    ioned
    -0.60
    DragonMagazine
    -0.59
     comrades
    -0.59
    POSITIVE LOGITS
     Indies
    0.88
     Alps
    0.88
     Midwest
    0.87
     illegally
    0.86
     mainland
    0.86
     Isles
    0.85
     Territories
    0.84
     marketplace
    0.81
    .?
    0.78
    .,
    0.76
    Activations Density 0.133%

    No Known Activations