© 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. 12615
    Prev
    Next
    INDEX
    Explanations

    comparative statements and hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and expressions of uncertainty

    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
    QB
    -0.50
    habi
    -0.50
    imb
    -0.49
    qt
    -0.48
    PRES
    -0.47
    onite
    -0.46
    zinski
    -0.46
    chenko
    -0.46
    anchez
    -0.45
    igers
    -0.45
    POSITIVE LOGITS
    etheless
    0.58
     ceases
    0.57
     happens
    0.56
     importantly
    0.55
     arises
    0.53
     hath
    0.52
     Sakuya
    0.52
     informs
    0.52
     glim
    0.51
     decides
    0.51
    Activations Density 1.451%

    No Known Activations