© 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. 12-RES-JB
    11. 4921
    Prev
    Next
    INDEX
    Explanations

    specific names of locations or characters

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    occurrences of the name "Sh" or variations of it, possibly representing an important character or theme within the context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    PDATE
    -0.84
    CLASSIFIED
    -0.84
     hypers
    -0.80
     Alexandria
    -0.78
     Palmer
    -0.76
     football
    -0.75
     basketball
    -0.74
     sparing
    -0.74
     procedural
    -0.74
     Titanic
    -0.72
    POSITIVE LOGITS
    Å«
    1.57
    ogun
    1.52
    Åį
    1.51
    ugen
    1.51
    into
    1.49
    onen
    1.48
    igure
    1.45
    imb
    1.45
    inki
    1.44
    ibu
    1.41
    Activations Density 0.028%

    No Known Activations