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

    Neuronpedia

    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. 3-RES-JB
    11. 620
    Prev
    Next
    INDEX
    Explanations

    governmental entities, specific locations, and legal terms, particularly related to states

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or geographic entity

    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
    poons
    -0.98
    ghazi
    -0.84
    ogle
    -0.81
    ãĥīãĥ©
    -0.80
     Maw
    -0.77
    edin
    -0.75
    bats
    -0.75
    emis
    -0.73
    iries
    -0.66
    sett
    -0.66
    POSITIVE LOGITS
     legislature
    1.11
     legislatures
    1.07
     Legislature
    1.02
    wide
    0.98
     legislator
    0.86
     legislators
    0.84
     senator
    0.82
     governments
    0.81
     senate
    0.79
     lawmakers
    0.79
    Activations Density 0.068%

    No Known Activations