© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 266
    Prev
    Next
    INDEX
    Explanations

    phrases related to assigning responsibility and taking action

    oai_token-act-pair · gpt-3.5-turbo

    the end of text markers

    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
    Ĥİ
    -0.64
    :(
    -0.64
    :[
    -0.60
    uta
    -0.59
    éŃĶ
    -0.56
    )[
    -0.54
    Shut
    -0.53
    odcast
    -0.53
    ¶
    -0.53
    .<
    -0.52
    POSITIVE LOGITS
     consequently
    0.93
     therefore
    0.91
     hence
    0.90
     thus
    0.87
     then
    0.84
     thereby
    0.80
     possibly
    0.75
     vice
    0.75
    rogen
    0.75
     thence
    0.74
    Activations Density 0.837%

    No Known Activations