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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 1842
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons or evaluations

    oai_token-act-pair · gpt-3.5-turbo

    negations or expressions that indicate absence or limitations

    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
    culosis
    -0.67
    alion
    -0.67
    icism
    -0.65
    CRE
    -0.64
    bara
    -0.63
    EMA
    -0.62
    erity
    -0.62
    Domain
    -0.61
    arius
    -0.60
    ario
    -0.60
    POSITIVE LOGITS
    abouts
    0.93
     themselves
    0.90
     interchangeable
    0.80
    selves
    0.77
    types
    0.75
     extensions
    0.75
     selves
    0.75
     equivalents
    0.72
    models
    0.72
    products
    0.72
    Activations Density 1.056%

    No Known Activations