© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 19443
    Prev
    Next
    INDEX
    Explanations

    references to leaders or authority figures

    oai_token-act-pair · gpt-3.5-turbo

    references to coaches in the context of sports

    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
     Suc
    -0.68
     sax
    -0.65
     autos
    -0.65
     Reincarn
    -0.63
     IMAGES
    -0.62
    PsyNetMessage
    -0.61
     msec
    -0.60
    aneously
    -0.59
    9999
    -0.58
     subp
    -0.58
    POSITIVE LOGITS
    liners
    1.18
    canon
    1.12
    liner
    1.10
    quarter
    1.07
    quarters
    1.05
    lining
    1.05
    quartered
    1.05
    gear
    1.04
    shots
    1.03
    hunter
    1.02
    Activations Density 0.030%

    No Known Activations