© 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. 3-RES-JB
    11. 534
    Prev
    Next
    INDEX
    Explanations

    numerical ages mentioned in news articles

    oai_token-act-pair · gpt-3.5-turbo

    numeric values associated with ages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hegemony
    -0.75
    eus
    -0.69
    Reviewer
    -0.68
    rill
    -0.66
    netflix
    -0.66
     brill
    -0.65
    imaru
    -0.65
    widget
    -0.64
     gimm
    -0.63
    kered
    -0.62
    POSITIVE LOGITS
    th
    0.89
    %"
    0.89
     Minutes
    0.84
    een
    0.83
    eenth
    0.82
     Investig
    0.81
     minutes
    0.80
     acres
    0.80
    ½
    0.79
    teen
    0.77
    Activations Density 0.365%

    No Known Activations