© 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. 4737
    Prev
    Next
    INDEX
    Explanations

    vulnerable situations involving physical or emotional harm and distress

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

    expressions of inability or obligation

    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
    senal
    -1.22
    ò
    -1.15
    EStream
    -1.11
    ñ
    -1.10
    çīĪ
    -1.09
     teasp
    -1.07
    Þ
    -1.07
    isSpecial
    -1.06
    ß
    -1.06
    ý
    -1.04
    POSITIVE LOGITS
     forgive
    1.20
     cry
    1.07
     endure
    1.06
     blame
    1.01
     cope
    1.01
     apologize
    1.01
     weep
    1.01
     admit
    1.00
     scream
    1.00
     apologise
    0.99
    Activations Density 0.392%

    No Known Activations