© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 23982
    Prev
    Next
    INDEX
    Explanations

    keywords or phrases indicating information sections, such as "Read the detailed explanation," or "Watch the full interview."

    oai_token-act-pair · gpt-3.5-turbo

    symbols and formatting within the text

    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
    anmar
    -0.81
    orical
    -0.80
    nuts
    -0.78
    bably
    -0.74
    itably
    -0.74
    itionally
    -0.71
    orically
    -0.71
    orescence
    -0.69
    nut
    -0.69
     sidel
    -0.68
    POSITIVE LOGITS
    »
    1.05
     »
    0.88
     Quote
    0.76
    Ü
    0.74
    CLASSIFIED
    0.74
    ////////////////////////////////
    0.73
    ETS
    0.70
     <!--
    0.69
     «
    0.68
     âĢº
    0.68
    Activations Density 0.009%

    No Known Activations