© 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. 15501
    Prev
    Next
    INDEX
    Explanations

    references to a specific place named "Montclair."

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the name "Mont."

    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
    pta
    -0.81
    ACTED
    -0.79
    Thumbnail
    -0.78
    glers
    -0.76
    ãģĦ
    -0.75
    æĢ
    -0.72
    DragonMagazine
    -0.70
    ÃŁ
    -0.68
    ãĥį
    -0.67
     menstrual
    -0.65
    POSITIVE LOGITS
    erey
    1.05
    fort
    1.03
    agne
    0.97
    essor
    0.94
     Blanc
    0.92
    gomery
    0.92
     Seym
    0.86
    ré
    0.85
    agu
    0.84
    oya
    0.84
    Activations Density 0.007%

    No Known Activations