© 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. 10-RES-JB
    11. 6563
    Prev
    Next
    INDEX
    Explanations

    phrases related to publishing, broadcasting, and copyrighting materials

    oai_token-act-pair · gpt-3.5-turbo

    terms related to copyright and publication restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Samantha
    -0.61
    vae
    -0.58
     jug
    -0.57
    zers
    -0.56
    naires
    -0.56
    hift
    -0.55
    href
    -0.54
     Slot
    -0.54
     Incredible
    -0.53
     tal
    -0.52
    POSITIVE LOGITS
    çīĪ
    0.72
    ioned
    0.56
    ÑĢ
    0.56
    ÏĢ
    0.55
    atform
    0.55
    sson
    0.55
    IPP
    0.55
    renheit
    0.55
     patented
    0.53
    entimes
    0.52
    Activations Density 0.041%

    No Known Activations