© 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. 2633
    Prev
    Next
    INDEX
    Explanations

    incoherent strings of text with a medical/safety context

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

    instances of incomprehensible or unclear speech

    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
    illions
    -0.61
    ,
    -0.58
    =-=-=-=-
    -0.57
    iest
    -0.53
    illion
    -0.53
    :
    -0.51
    -
    -0.49
    ,—
    -0.48
    lessly
    -0.48
    .
    -0.47
    POSITIVE LOGITS
     withd
    0.38
     CLIENT
    0.35
     confir
    0.35
     behavi
    0.35
     maternal
    0.34
     Reprodu
    0.34
     showc
    0.34
     android
    0.33
     menstrual
    0.33
     fetal
    0.32
    Activations Density 2.643%

    No Known Activations