© 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. 21216
    Prev
    Next
    INDEX
    Explanations

    numerical expressions and indefinite quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to multiple studies or instances

    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
    gt
    -0.81
    Dialogue
    -0.74
    deen
    -0.74
    brance
    -0.74
    dl
    -0.74
    minus
    -0.73
    tre
    -0.70
    unity
    -0.69
     Sgt
    -0.68
    nothing
    -0.65
    POSITIVE LOGITS
     studies
    1.68
     factors
    1.38
     experts
    1.36
     researchers
    1.36
     commentators
    1.33
     scholars
    1.33
     jurisdictions
    1.29
     countries
    1.28
     resear
    1.27
     analyses
    1.26
    Activations Density 0.229%

    No Known Activations