© 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. 24320
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific conclusions or study findings

    oai_token-act-pair · gpt-3.5-turbo

    conclusive statements related to research findings or analyses

    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
     Salon
    -0.78
     âĨĴ
    -0.76
    Thor
    -0.75
     ______
    -0.70
    vae
    -0.68
    llah
    -0.66
    VICE
    -0.66
    raits
    -0.66
    itus
    -0.64
     Therapy
    -0.64
    POSITIVE LOGITS
    ufact
    0.85
    atche
    0.73
    emic
    0.68
     flaw
    0.67
    abase
    0.67
    theless
    0.64
    acebook
    0.64
     Gorge
    0.63
     oun
    0.63
     suprem
    0.63
    Activations Density 0.000%

    No Known Activations