© 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. 9-RES-JB
    11. 7316
    Prev
    Next
    INDEX
    Explanations

    distances in kilometers and miles, specifically the shorter distance in parenthesis followed by the longer one

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (&
    -0.67
    natureconservancy
    -0.66
    Ļ½
    -0.65
    CLOSE
    -0.61
    ([
    -0.60
    :(
    -0.60
    (
    -0.59
    ãĥ¥
    -0.58
    tnc
    -0.57
    ibles
    -0.57
    POSITIVE LOGITS
     apiece
    0.77
    ãĥİ
    0.69
     devoted
    0.64
    +.
    0.61
     dedicated
    0.60
    illon
    0.59
    ridges
    0.59
     respectively
    0.58
    +)
    0.56
     reserved
    0.56
    Activations Density 0.083%

    No Known Activations