© 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. 4761
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism or scrutiny of individuals and situations

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

    instances of the word "especially" and similar modifiers indicating emphasis or particularity

    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
    ilib
    -0.73
    orc
    -0.69
    opus
    -0.67
    ãĥ¼ãĥĨãĤ£
    -0.66
    bridge
    -0.65
    urst
    -0.63
    ãĤ¡
    -0.60
    doctor
    -0.59
    alter
    -0.59
    ru
    -0.58
    POSITIVE LOGITS
     considering
    1.15
     since
    1.10
     given
    1.00
     insofar
    0.90
     if
    0.89
     when
    0.89
     compared
    0.85
     regarding
    0.84
     concerning
    0.82
     after
    0.81
    Activations Density 0.097%

    No Known Activations