© 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. 2-RES-JB
    11. 527
    Prev
    Next
    INDEX
    Explanations

    the word "cat" within text

    oai_token-act-pair · gpt-4-turbo

    occurrences of the word "cat," particularly with different variations such as capitalized or combined with other words

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "cat."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vander
    -0.73
     DPR
    -0.67
     Gree
    -0.67
    mble
    -0.67
     Fargo
    -0.65
     steroids
    -0.64
     Vaugh
    -0.63
     Matter
    -0.62
     Cere
    -0.61
    uden
    -0.60
    POSITIVE LOGITS
    cat
    1.35
    aclysm
    1.27
    alogue
    1.25
    alog
    1.24
    alyst
    1.22
    apult
    1.17
    hedral
    1.10
    Cat
    1.06
    cats
    1.05
    heter
    1.00
    Activations Density 0.008%

    No Known Activations