© 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. 4840
    Prev
    Next
    INDEX
    Explanations

    phrases related to possession or ownership

    oai_token-act-pair · gpt-3.5-turbo

    instances of consent and authority in various contexts

    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
    monton
    -0.63
    coord
    -0.63
    8000
    -0.61
    elong
    -0.60
    stanbul
    -0.59
    ãĥī
    -0.58
    mes
    -0.58
    arc
    -0.57
    react
    -0.57
    alys
    -0.56
    POSITIVE LOGITS
     without
    1.92
    without
    1.87
     Without
    1.74
     WITHOUT
    1.66
    Without
    1.62
     absence
    1.20
     sans
    1.19
     devoid
    1.15
     lacking
    1.10
    minus
    1.07
    Activations Density 0.182%

    No Known Activations