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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 23696
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "integral" being an important part of something

    oai_token-act-pair · gpt-3.5-turbo

    the concept of essential components or elements within various contexts

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

    No Comments

    Negative Logits
    Ö¼
    -0.71
    ÃĥÃĤ
    -0.69
    ilk
    -0.69
    ander
    -0.69
    haw
    -0.68
    thur
    -0.67
    kers
    -0.63
    bare
    -0.63
    ammers
    -0.62
     Drugs
    -0.62
    POSITIVE LOGITS
     integral
    0.90
     adjunct
    0.81
     parts
    0.74
     component
    0.74
    isin
    0.74
     part
    0.73
    onite
    0.72
    SourceFile
    0.70
     accompan
    0.70
     aspects
    0.69
    Activations Density 0.013%

    No Known Activations