© 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. 16143
    Prev
    Next
    INDEX
    Explanations

    mentions of various labs and research institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to various laboratories and their activities

    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
    cuts
    -0.76
    making
    -0.74
    Args
    -0.74
    vict
    -0.72
     ACTIONS
    -0.72
    bal
    -0.71
    ful
    -0.70
    sett
    -0.69
    conv
    -0.67
    leness
    -0.66
    POSITIVE LOGITS
     Laboratories
    0.99
    creen
    0.97
     Labs
    0.96
    hiba
    0.95
    ource
    0.92
    cius
    0.86
    ynthesis
    0.85
    mith
    0.83
    orer
    0.81
     labs
    0.81
    Activations Density 0.020%

    No Known Activations