© 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. 4-RES-JB
    11. 9308
    Prev
    Next
    INDEX
    Explanations

    names possibly surrounding a political or military context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "boo" and related variations

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

    No Comments

    Negative Logits
    nesota
    -0.90
    idency
    -0.87
    pmwiki
    -0.85
    Interstitial
    -0.84
    ULTS
    -0.76
    EDIT
    -0.73
    ixture
    -0.71
    pite
    -0.70
    olars
    -0.70
    OPE
    -0.69
    POSITIVE LOGITS
    gey
    1.38
     boo
    1.30
    gee
    1.02
    Boo
    0.93
     Boo
    0.93
    etooth
    0.87
    zy
    0.86
    hovah
    0.85
    eful
    0.83
    leans
    0.80
    Activations Density 0.011%

    No Known Activations