© 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. 1-RES-JB
    11. 2531
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of specific entities

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and specific entities relevant to discussions or critiques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBLE
    -0.90
    poons
    -0.82
    ption
    -0.81
    Ö¼
    -0.76
    ighters
    -0.75
    eree
    -0.72
    ãĥ¼ãĥĨãĤ£
    -0.72
    mble
    -0.70
    æĢ
    -0.69
    ativity
    -0.68
    POSITIVE LOGITS
    kat
    0.86
     DPR
    0.84
    laus
    0.83
    lar
    0.83
    rieg
    0.82
    ofi
    0.81
    istani
    0.79
    lov
    0.77
     Helsinki
    0.73
     Kat
    0.73
    Activations Density 0.034%

    No Known Activations