© 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. 14331
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantities or limits related to increasing numbers

    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
     Lack
    -0.61
     Fug
    -0.59
    furt
    -0.58
     conduc
    -0.57
     Cele
    -0.55
    士
    -0.54
     Mate
    -0.54
     felon
    -0.53
    ulhu
    -0.53
     Ezek
    -0.52
    POSITIVE LOGITS
    regulated
    1.04
    regulation
    1.03
     to
    1.02
    graded
    1.01
    grading
    0.93
    sized
    0.89
    grades
    0.86
    cycl
    0.86
    gradient
    0.86
    bring
    0.86
    Activations Density 0.050%

    No Known Activations