© 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. 3-RES-JB
    11. 15448
    Prev
    Next
    INDEX
    Explanations

    mentions of specific technological devices or applications

    oai_token-act-pair · gpt-3.5-turbo

    topics related to regulations and controversies surrounding substances and vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Warn
    -0.74
    SN
    -0.72
    hillary
    -0.65
     Wein
    -0.65
    vern
    -0.64
    Us
    -0.60
    nen
    -0.60
    rawdownloadcloneembedreportprint
    -0.60
     Neh
    -0.59
    herty
    -0.59
    POSITIVE LOGITS
    eers
    0.89
    ternity
    0.89
    ertodd
    0.82
    merce
    0.79
    ioxide
    0.77
     syndrome
    0.74
    Initialized
    0.72
    cellence
    0.69
    uyomi
    0.69
     disorder
    0.69
    Activations Density 0.385%

    No Known Activations