© 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. 1-RES-JB
    11. 20090
    Prev
    Next
    INDEX
    Explanations

    terms related to specific geographic locations, specifically focusing on Clemson University and various cities or states

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of places and sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kens
    -0.81
    raid
    -0.78
    road
    -0.77
    mentation
    -0.72
    glers
    -0.71
    href
    -0.71
    hab
    -0.70
    akespe
    -0.70
    lopp
    -0.69
    rett
    -0.68
    POSITIVE LOGITS
     Nadu
    1.25
    mson
    1.14
    avage
    0.88
    itri
    0.82
     partName
    0.78
    ciples
    0.75
     Clemson
    0.74
    enegger
    0.74
     Tian
    0.72
     Primordial
    0.71
    Activations Density 0.020%

    No Known Activations