© 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. 9-RES-JB
    11. 1562
    Prev
    Next
    INDEX
    Explanations

    phrases that mention both state and local governments

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "and" used in various contexts related to governance and funding

    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
     Wheels
    -0.73
    bos
    -0.73
     charms
    -0.72
     Picks
    -0.72
     pedals
    -0.71
     buttons
    -0.70
     Pigs
    -0.69
     Stall
    -0.69
     Statements
    -0.68
     Malk
    -0.68
    POSITIVE LOGITS
     regional
    1.08
     international
    1.05
    heastern
    1.05
    incial
    1.00
     provincial
    0.94
     allied
    0.92
     local
    0.92
     municipal
    0.90
    azeera
    0.89
     global
    0.89
    Activations Density 0.090%

    No Known Activations