© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 14607
    Prev
    Next
    INDEX
    Explanations

    words related to individuals or entities, specifically focusing on proper nouns related to names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    people's names or location names ending with 'row'

    oai_token-act-pair · gpt-3.5-turbo
    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
    ngth
    -0.73
    dimension
    -0.68
    ascus
    -0.65
    bern
    -0.64
    shape
    -0.63
    URA
    -0.63
     Remastered
    -0.62
    iland
    -0.62
    Drive
    -0.59
    ĨĴ
    -0.57
    POSITIVE LOGITS
    enture
    0.76
    aroo
    0.74
     Explosion
    0.67
    hea
    0.65
    ĵĺ
    0.65
     teasp
    0.64
     Admission
    0.64
    oola
    0.64
    hemy
    0.63
    ħĭ
    0.63
    Activations Density 0.101%

    No Known Activations