© 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. 5263
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "ass"

    oai_token-act-pair · gpt-3.5-turbo
    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
     Expend
    -0.66
    tc
    -0.61
     cf
    -0.61
     bite
    -0.60
    MSN
    -0.59
     Borders
    -0.57
     vacc
    -0.56
     stall
    -0.56
     empt
    -0.55
     fright
    -0.54
    POSITIVE LOGITS
    assin
    1.50
    ociation
    1.33
    oci
    1.28
    ett
    1.21
    istant
    1.18
    ociate
    1.17
    istance
    1.14
    idy
    1.13
    andra
    1.11
    essment
    1.09
    Activations Density 0.041%

    No Known Activations