© 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. 5106
    Prev
    Next
    INDEX
    Explanations

    references to medical emergencies and assistance in terms of treatment or financial support

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

    elements of narratives related to personal challenges and community support

    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
    vez
    -0.89
     Viper
    -0.87
     snake
    -0.84
    awar
    -0.83
    azor
    -0.78
    illac
    -0.78
    YC
    -0.72
     Isis
    -0.72
    ulla
    -0.72
    quer
    -0.69
    POSITIVE LOGITS
    Frank
    2.19
     Frank
    1.98
     Franken
    1.76
     Franklin
    1.76
     Franks
    1.59
    fr
    1.56
    Fr
    1.54
     FR
    1.46
     Fr
    1.46
     Frankie
    1.44
    Activations Density 0.207%

    No Known Activations