© 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. 0-RES-JB
    11. 5365
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and opinions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "is"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prominently
    -0.63
    efully
    -0.63
    ected
    -0.61
    âĸ¬âĸ¬
    -0.58
    ASED
    -0.57
    PDATE
    -0.57
    ADRA
    -0.57
    chnology
    -0.54
    ãĤ´ãĥ³
    -0.54
     exting
    -0.53
    POSITIVE LOGITS
    s
    3.40
    sb
    1.67
    sie
    1.64
    si
    1.64
    ski
    1.56
    ses
    1.52
    sa
    1.51
    sin
    1.49
    sburg
    1.49
    sg
    1.48
    Activations Density 0.420%

    No Known Activations