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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 1944
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations and border disputes

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and location names

    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
     nails
    -0.73
    writer
    -0.67
     disemb
    -0.66
     beams
    -0.64
     pedals
    -0.64
     mate
    -0.64
     resc
    -0.63
     punches
    -0.63
     crank
    -0.63
     tears
    -0.63
    POSITIVE LOGITS
     district
    1.02
    qqa
    0.98
     Peninsula
    0.97
     Valley
    0.96
    area
    0.96
     peninsula
    0.95
    atown
    0.95
     Highlands
    0.95
     Province
    0.95
    arat
    0.94
    Activations Density 0.289%

    No Known Activations