© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 1402
    Prev
    Next
    INDEX
    Explanations

    HTML anchor tags (a href="...") and related elements in text

    oai_token-act-pair · gpt-3.5-turbo

    HTML elements and their attributes

    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
    erous
    -0.72
    vell
    -0.69
    packing
    -0.65
     installations
    -0.64
    ansky
    -0.64
     Cheong
    -0.63
    oshenko
    -0.63
    wagen
    -0.62
    umatic
    -0.61
    dies
    -0.61
    POSITIVE LOGITS
    ><
    1.60
    >
    1.52
    >(
    1.44
    ></
    1.41
    >)
    1.33
    >,
    1.33
    />
    1.30
    >[
    1.28
    >"
    1.28
    >:
    1.23
    Activations Density 0.029%

    No Known Activations