© 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. 1-RES-JB
    11. 13032
    Prev
    Next
    INDEX
    Explanations

    mentions of programs or initiatives, often involving government or organizational efforts

    oai_token-act-pair · gpt-3.5-turbo

    references to various "schemes" related to policies or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cknowled
    -0.68
    ulu
    -0.67
     Patriarch
    -0.59
     doubt
    -0.58
    interrupted
    -0.57
     rapt
    -0.57
    inas
    -0.57
    ente
    -0.56
    iu
    -0.56
     resurg
    -0.56
    POSITIVE LOGITS
     scheme
    1.41
     schemes
    1.39
     Scheme
    1.10
    eering
    0.77
    urally
    0.77
    hess
    0.73
    ĸļ
    0.73
     devised
    0.72
    matically
    0.72
    escape
    0.71
    Activations Density 0.010%

    No Known Activations