© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 15986
    Prev
    Next
    INDEX
    Explanations

    mentions of statistical data and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "according to" which indicates sources or references in statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exting
    -0.88
     eleph
    -0.81
     submar
    -0.78
     helicop
    -0.65
     conclud
    -0.64
     fuss
    -0.62
    otor
    -0.62
    ²¾
    -0.61
    Þ
    -0.61
    ailability
    -0.59
    POSITIVE LOGITS
     to
    0.91
     Nielsen
    0.78
     surveys
    0.77
     estimates
    0.74
     Reuters
    0.69
     Census
    0.68
    %]
    0.68
     POLITICO
    0.68
     data
    0.68
     Gallup
    0.67
    Activations Density 0.042%

    No Known Activations