© 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. 1-RES-JB
    11. 3729
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to routine or the ordinary

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "usual" experiences or occurrences

    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
     Starship
    -0.87
    rift
    -0.81
    kamp
    -0.81
    haw
    -0.79
    raped
    -0.77
    bec
    -0.75
    sten
    -0.75
    mented
    -0.75
    hani
    -0.74
    onics
    -0.73
    POSITIVE LOGITS
     disclaimer
    0.85
     usual
    0.83
     suspects
    0.81
     è£ıè¦ļéĨĴ
    0.80
     mosqu
    0.79
    ITIES
    0.77
     disclaim
    0.76
     deviations
    0.76
     err
    0.75
     deviation
    0.73
    Activations Density 0.007%

    No Known Activations