© 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. 8-RES-JB
    11. 23901
    Prev
    Next
    INDEX
    Explanations

    words related to famous locations or people within a specific setting

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names, particularly related to places and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taboola
    -0.67
    wagen
    -0.63
    _>
    -0.62
     sshd
    -0.62
    ĨĴ
    -0.60
    ¬¼
    -0.60
    omore
    -0.59
     panc
    -0.59
     liter
    -0.59
    ĸļ
    -0.59
    POSITIVE LOGITS
    aline
    0.91
    istration
    0.86
    andise
    0.77
    ause
    0.77
    vertisement
    0.75
    phe
    0.74
    acent
    0.72
    asio
    0.71
    itness
    0.71
    onement
    0.70
    Activations Density 0.055%

    No Known Activations