© 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. 0-RES-JB
    11. 7837
    Prev
    Next
    INDEX
    Explanations

    locations, specifically focusing on places containing "Nev" or "Julia"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations and names, particularly in relation to people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bomber
    -0.92
    Ali
    -0.82
    Oil
    -0.81
     BASE
    -0.79
    draft
    -0.78
     Shiite
    -0.75
    Template
    -0.73
     Lac
    -0.71
    tm
    -0.71
     Tradition
    -0.71
    POSITIVE LOGITS
     Nev
    1.98
    Nev
    1.59
     Julia
    1.50
     Gunn
    1.34
    vind
    1.34
     AV
    1.16
    nn
    1.15
     Shen
    1.13
     vind
    1.10
     Neville
    1.10
    Activations Density 0.062%

    No Known Activations