© 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. 7-RES-JB
    11. 23648
    Prev
    Next
    INDEX
    Explanations

    ages or dates indicating someone's age

    oai_token-act-pair · gpt-3.5-turbo

    numerical age milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spill
    -0.65
    kered
    -0.63
     retali
    -0.63
     ambush
    -0.63
     roundup
    -0.63
     demonstration
    -0.62
     quotation
    -0.60
     diversion
    -0.60
    ttes
    -0.60
     outage
    -0.59
    POSITIVE LOGITS
     years
    0.92
    ½
    0.91
    yo
    0.88
    years
    0.87
    yrs
    0.83
    mph
    0.82
    %.
    0.79
     cents
    0.79
     Years
    0.77
    %,
    0.77
    Activations Density 0.096%

    No Known Activations