© 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. 7-RES-JB
    6. 5253
    Prev
    Next
    INDEX
    Explanations

    country names

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and names, particularly related to places and people

    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
    querque
    -0.81
    acho
    -0.71
    ãĥīãĥ©
    -0.71
    ã
    -0.68
    ibrary
    -0.67
    cious
    -0.67
    ICAN
    -0.65
    ļé
    -0.65
    ģ«
    -0.65
    tumblr
    -0.65
    POSITIVE LOGITS
    ingen
    0.77
    nesday
    0.76
    ÅĤ
    0.65
     Lithuania
    0.65
    hots
    0.64
    anders
    0.63
     Kyr
    0.62
    urat
    0.62
     Aden
    0.61
    puff
    0.61
    Activations Density 0.746%

    No Known Activations