© 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. 4787
    Prev
    Next
    INDEX
    Explanations

    statistics and percentages described in relation to political figures and opinions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    quantitative comparisons and statistics regarding public opinion on political issues

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ě
    -1.07
    ė
    -1.07
    ă
    -1.07
    ÿ
    -1.06
    ú
    -1.06
    embedreportprint
    -1.06
    Ę
    -1.06
    ā
    -1.06
    Ē
    -1.06
    ø
    -1.06
    POSITIVE LOGITS
     11
    0.83
     14
    0.83
     13
    0.83
     9
    0.82
     16
    0.81
     17
    0.81
     15
    0.81
     12
    0.81
     8
    0.80
     19
    0.80
    Activations Density 0.336%

    No Known Activations