© 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. 10-RES-JB
    11. 14057
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations or entities associated with names that start with "M."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CBI
    -0.69
     counsel
    -0.56
     podium
    -0.55
     microwave
    -0.55
     Apollo
    -0.54
     NRS
    -0.54
     [*]
    -0.53
    ECTION
    -0.53
     Crescent
    -0.53
     desks
    -0.53
    POSITIVE LOGITS
    ufact
    0.94
    arella
    0.91
    udi
    0.89
    gage
    0.88
    waukee
    0.88
    intosh
    0.86
    enzie
    0.86
    ICAN
    0.85
    nesota
    0.84
    ilage
    0.83
    Activations Density 0.086%

    No Known Activations