© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 15863
    Prev
    Next
    INDEX
    Explanations

    phrases indicating proximity or distance, especially in relation to a specific location or object

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate proximity or nearness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lace
    -0.74
    tec
    -0.67
    ply
    -0.66
    ple
    -0.66
    di
    -0.65
    mat
    -0.64
    PORT
    -0.64
    rod
    -0.64
    mit
    -0.64
    mie
    -0.63
    POSITIVE LOGITS
    isine
    0.94
    ieth
    0.89
    ¥ŀ
    0.89
    imore
    0.88
    ĨĴ
    0.80
    ĵĺ
    0.79
     Survive
    0.75
    ruciating
    0.75
    ħĭ
    0.75
     oun
    0.73
    Activations Density 0.023%

    No Known Activations