© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 10632
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or regions

    oai_token-act-pair · gpt-3.5-turbo

    references to America and its geographical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PDATE
    -0.80
    BIL
    -0.71
     practition
    -0.69
     submar
    -0.68
    olkien
    -0.65
     pione
    -0.65
    ThumbnailImage
    -0.62
    ActionCode
    -0.61
     Soda
    -0.60
     Nikki
    -0.60
    POSITIVE LOGITS
     globe
    0.80
     aisle
    0.79
    annels
    0.72
     borders
    0.71
     seams
    0.71
     continents
    0.71
    amer
    0.70
     corners
    0.67
    erences
    0.67
     distances
    0.67
    Activations Density 0.268%

    No Known Activations