© 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. 7-RES-JB
    11. 13837
    Prev
    Next
    INDEX
    Explanations

    names of individuals, potentially from news articles or legal reports

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically personal names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GoldMagikarp
    -0.85
    ModLoader
    -0.82
    PDATE
    -0.69
    CONT
    -0.66
    risome
    -0.65
    VW
    -0.64
    Congratulations
    -0.64
    Politics
    -0.64
    lvl
    -0.64
     enthusi
    -0.62
    POSITIVE LOGITS
    sson
    1.11
    ovich
    0.92
     Morse
    0.87
    kson
    0.86
    enson
    0.83
     III
    0.79
    owski
    0.77
    icum
    0.76
    chini
    0.76
    eson
    0.75
    Activations Density 0.157%

    No Known Activations