© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 7-RES-JB
    11. 14211
    Prev
    Next
    INDEX
    Explanations

    names or references to a specific person named Ann

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Ann."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    vous
    -0.84
    EStreamFrame
    -0.78
    raltar
    -0.76
    xual
    -0.76
    ierrez
    -0.75
    acters
    -0.70
    geoning
    -0.69
     membrane
    -0.68
    */(
    -0.67
     dare
    -0.66
    POSITIVE LOGITS
    ihilation
    1.28
    abeth
    1.24
    ounces
    1.23
    iversary
    1.23
    ihil
    1.23
     Arbor
    1.21
    abel
    1.21
    ouncing
    1.19
    ounced
    1.18
    unciation
    1.18
    Activations Density 0.019%

    No Known Activations