© 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. 9850
    Prev
    Next
    INDEX
    Explanations

    numbers indicating someone's age

    oai_token-act-pair · gpt-3.5-turbo

    instances of age-related phrases

    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
     Scrib
    -0.73
     Tac
    -0.66
    imaru
    -0.63
    zsche
    -0.60
    Ń·
    -0.60
     Twain
    -0.58
     abl
    -0.57
     noise
    -0.57
     Mechdragon
    -0.57
     Nil
    -0.57
    POSITIVE LOGITS
    olds
    1.05
    appointed
    1.03
    old
    1.00
    degree
    0.94
    prison
    0.89
    plus
    0.80
    aunts
    0.80
    OLD
    0.79
    sized
    0.79
    inch
    0.78
    Activations Density 0.034%

    No Known Activations