© 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. 11-RES-JB
    11. 3418
    Prev
    Next
    INDEX
    Explanations

    contractions with "n't"

    oai_token-act-pair · gpt-3.5-turbo

    negative statements or sentiments expressed in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.71
    Occ
    -0.67
    inet
    -0.62
    ophe
    -0.61
    olphin
    -0.60
    sequent
    -0.60
     Lob
    -0.59
     Toad
    -0.58
    acebook
    -0.58
    ially
    -0.58
    POSITIVE LOGITS
     want
    1.95
     WANT
    1.71
    want
    1.68
     wants
    1.65
     wanna
    1.56
     wanted
    1.55
     Want
    1.52
     crave
    1.39
     wanting
    1.38
     desire
    1.31
    Activations Density 0.210%

    No Known Activations