© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18859
    Prev
    Next
    INDEX
    Explanations

    phrases introducing new information or situations

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Expect
    -0.68
    */
    -0.64
    ggles
    -0.62
    Join
    -0.61
    fts
    -0.60
    iscover
    -0.60
    etermin
    -0.58
     Legislation
    -0.57
     Disorders
    -0.56
    Sit
    -0.55
    POSITIVE LOGITS
     resembled
    1.56
     consisted
    1.46
     amounted
    1.45
     lasted
    1.45
     resulted
    1.41
     culminated
    1.38
     differed
    1.34
     seemed
    1.34
     lacked
    1.31
     hadn
    1.26
    Activations Density 0.248%

    No Known Activations