© 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. 10287
    Prev
    Next
    INDEX
    Explanations

    dates in various formats

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that contain isolated high-activation tokens, indicating potential errors or formatting issues

    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
     eleph
    -0.77
     prec
    -0.77
     respons
    -0.75
     displacement
    -0.74
     exha
    -0.73
     themselves
    -0.73
     scrap
    -0.72
     branches
    -0.72
     duty
    -0.71
     cons
    -0.71
    POSITIVE LOGITS
    WASHINGTON
    1.52
    TOR
    1.41
    Posted
    1.41
    Updated
    1.39
    LOS
    1.37
    SAN
    1.36
    DEN
    1.36
    Introduction
    1.36
    Abstract
    1.35
    Published
    1.35
    Activations Density 0.133%

    No Known Activations