© 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. 4-RES-JB
    11. 4299
    Prev
    Next
    INDEX
    Explanations

    multiple variations of the word "thumb"

    oai_token-act-pair · gpt-3.5-turbo

    the word "symbol" and its variations or forms

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

    No Comments

    Negative Logits
    ãĥīãĥ©ãĤ´ãĥ³
    -0.75
    coni
    -0.74
    zona
    -0.72
    Interstitial
    -0.69
    AMS
    -0.68
     è£ı
    -0.68
    Ô
    -0.63
    BALL
    -0.63
    ãĥ³ãĤ¸
    -0.63
    fully
    -0.63
    POSITIVE LOGITS
    ilib
    1.15
    olicy
    0.98
    edded
    0.97
    iotic
    0.97
    iotics
    0.92
    uild
    0.89
    odies
    0.88
    ortal
    0.87
    iosis
    0.84
    illion
    0.84
    Activations Density 0.011%

    No Known Activations