© 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. 23785
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Matthew" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    names related to individuals, particularly those that include variations of the name "Mat" or "Matt."

    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
    xual
    -0.81
    vironment
    -0.73
    士
    -0.71
    ĨĴ
    -0.71
    è»
    -0.69
    mercial
    -0.69
    etheless
    -0.68
    avorite
    -0.68
     phosphate
    -0.67
    Ħ¢
    -0.67
    POSITIVE LOGITS
    ilda
    1.09
    hews
    1.05
    rin
    0.97
    hew
    0.95
    chen
    0.89
    terson
    0.89
    rox
    0.88
    ruck
    0.88
    riot
    0.87
    nick
    0.87
    Activations Density 0.048%

    No Known Activations