© 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. 5123
    Prev
    Next
    INDEX
    Explanations

    phrases related to political actions or reactions

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

    actions and behaviors of individuals, particularly in moral or contentious contexts

    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
    ixels
    -0.73
    ickets
    -0.73
    burn
    -0.69
    ciating
    -0.69
    atari
    -0.66
    coming
    -0.65
    felt
    -0.65
    isSpecialOrderable
    -0.64
    Graphics
    -0.63
     Landing
    -0.63
    POSITIVE LOGITS
     strangely
    1.10
    uate
    1.09
     impuls
    1.09
     responsibly
    1.06
     decisively
    1.02
     arrog
    1.02
     autonom
    1.01
     unilaterally
    1.01
     inconsist
    1.00
     accordingly
    0.98
    Activations Density 0.055%

    No Known Activations