© 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. 1-RES-JB
    11. 16182
    Prev
    Next
    INDEX
    Explanations

    references to physical locations

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the word "pike."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.85
    erest
    -0.71
    imester
    -0.68
     prefrontal
    -0.66
    Birth
    -0.63
    âĸº
    -0.62
    ptoms
    -0.61
     âĢİ
    -0.61
    oral
    -0.61
    evidence
    -0.60
    POSITIVE LOGITS
    ike
    1.03
    lihood
    0.89
    mens
    0.82
    iking
    0.82
    manship
    0.80
    ikes
    0.75
    ernel
    0.72
    ye
    0.71
    erous
    0.70
    y
    0.69
    Activations Density 0.008%

    No Known Activations