© 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. 10-RES-JB
    11. 4359
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the state of Alabama

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of Alabama

    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
    liness
    -0.84
    zl
    -0.80
    hent
    -0.76
    ronic
    -0.75
     Myster
    -0.75
    cules
    -0.73
    ku
    -0.73
    soDeliveryDate
    -0.72
    ages
    -0.72
    apest
    -0.71
    POSITIVE LOGITS
     Crimson
    0.95
     Tide
    0.88
    mingham
    0.79
     Ala
    0.77
     Alabama
    0.74
     senate
    0.72
     Hunts
    0.70
    abama
    0.69
    ļéĨĴ
    0.68
    Ļ½
    0.68
    Activations Density 0.043%

    No Known Activations