© 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. 3327
    Prev
    Next
    INDEX
    Explanations

    terms related to syllabus or educational material

    oai_token-act-pair · gpt-3.5-turbo

    references to syllables or specific names in the context of communication

    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
    velt
    -1.08
    eur
    -0.92
    holes
    -0.92
    arding
    -0.76
    bucks
    -0.76
    xual
    -0.74
    bor
    -0.73
     Protector
    -0.73
    vers
    -0.71
    Wil
    -0.71
    POSITIVE LOGITS
    kson
    0.94
     Bach
    0.84
    arma
    0.77
     syll
    0.76
    ittal
    0.74
    abus
    0.71
     mathemat
    0.71
    andi
    0.69
    enta
    0.69
    itto
    0.65
    Activations Density 0.024%

    No Known Activations