© 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. 4-RES-JB
    11. 16385
    Prev
    Next
    INDEX
    Explanations

    terms related to data and information handling, such as "records," "accounts," "patterns," "coupons," and "layers."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data, records, and organizational elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    âĸ¬
    -0.63
    ãĥ¼ãĥĨ
    -0.62
     Azerb
    -0.58
    Reason
    -0.54
    æµ
    -0.54
    Honest
    -0.53
     Niet
    -0.53
    âĢ¢âĢ¢
    -0.52
    Guard
    -0.52
    é¾įå
    -0.51
    POSITIVE LOGITS
    hip
    0.99
    mith
    0.99
    paces
    0.98
    peed
    0.92
    chool
    0.92
    creen
    0.91
    pace
    0.89
    poons
    0.89
    uggest
    0.88
    hooting
    0.87
    Activations Density 0.653%

    No Known Activations