© 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. 11-RES-JB
    11. 14886
    Prev
    Next
    INDEX
    Explanations

    references to US states, particularly South Carolina and North Carolina

    oai_token-act-pair · gpt-3.5-turbo

    references to the states of North and South Carolina

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.79
     foreigners
    -0.68
     captcha
    -0.68
    ãĤ¼
    -0.65
     grap
    -0.63
     Dalai
    -0.62
    ATURE
    -0.62
     councillors
    -0.61
    anguage
    -0.60
    odox
    -0.60
    POSITIVE LOGITS
     Carolina
    1.58
     Dakota
    1.52
     Alabama
    1.05
     Tennessee
    1.01
    western
    1.01
     Columbia
    1.01
     Texas
    0.97
     Florida
    0.97
    central
    0.96
     Bend
    0.95
    Activations Density 0.052%

    No Known Activations