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. 11-RES-JB
    6. 17893
    Prev
    Next
    INDEX
    Explanations

    references to a specific geographic location, specifically Northern Ireland

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of "Northern" in reference to geographical locations, particularly Northern Ireland

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transform
    -0.72
    awaru
    -0.71
    ulative
    -0.71
    atically
    -0.69
    agic
    -0.67
    ifice
    -0.66
    enger
    -0.65
    atted
    -0.65
    aldehyde
    -0.65
    uting
    -0.63
    POSITIVE LOGITS
     Hemisphere
    1.28
     Ireland
    1.16
     hemisphere
    1.10
     Territory
    1.09
     Lights
    1.09
     Liberties
    1.06
     Territories
    0.97
     Caucasus
    0.91
     Exposure
    0.90
     Cyprus
    0.82
    Activations Density 0.024%

    No Known Activations