© 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. 11-RES-JB
    11. 12916
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism or pressure towards someone or something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating being in a state of criticism or scrutiny

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    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_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    pt
    -0.79
     Polo
    -0.68
     Potion
    -0.67
    nis
    -0.66
    ents
    -0.66
     Disabled
    -0.66
    Completed
    -0.64
    guide
    -0.64
    0000000
    -0.64
     Converted
    -0.64
    POSITIVE LOGITS
     scrutiny
    1.47
     criticism
    1.30
     fire
    1.28
     pressure
    1.16
     intense
    1.13
     ridicule
    1.08
     attack
    1.08
     renewed
    1.05
     fierce
    1.05
     increasing
    1.01
    Activations Density 0.071%

    No Known Activations