© 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. 2525
    Prev
    Next
    INDEX
    Explanations

    Fortune 500 company names

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

    references to major corporations and entities, particularly in relation to environmental or social issues

    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
    ting
    -0.79
    itate
    -0.69
    alist
    -0.69
    ahoo
    -0.68
    anical
    -0.67
    ulously
    -0.66
    nia
    -0.65
    ted
    -0.65
    rified
    -0.65
    ibly
    -0.65
    POSITIVE LOGITS
    -
    1.27
    âĢIJ
    1.18
    âĢij
    1.18
    -'
    0.89
    -.
    0.88
    -)
    0.87
     versa
    0.87
    -[
    0.84
    -(
    0.80
    –
    0.79
    Activations Density 0.177%

    No Known Activations