© 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. 2-RES-JB
    11. 10421
    Prev
    Next
    INDEX
    Explanations

    terms related to introductions or introductory content

    oai_token-act-pair · gpt-3.5-turbo

    references to introductions or introductory concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Millennium
    -0.81
     Ivory
    -0.73
     Liang
    -0.62
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.62
    Trend
    -0.60
     Franks
    -0.59
     Pharmaceutical
    -0.59
     Chiefs
    -0.59
     Kingdoms
    -0.59
     Slayer
    -0.57
    POSITIVE LOGITS
    spection
    1.67
    spective
    1.48
    verted
    1.42
    vert
    1.12
    verts
    1.05
    itial
    0.96
    spect
    0.94
    regor
    0.92
    iors
    0.90
    verting
    0.89
    Activations Density 0.007%

    No Known Activations