© 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 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. 6-RES-JB
    11. 7891
    Prev
    Next
    INDEX
    Explanations

    names, specifically first names and surnames

    oai_token-act-pair · gpt-3.5-turbo

    names that begin with the letter "M" or have "Matt" as a prefix

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parcels
    -0.71
    Ô
    -0.69
    alach
    -0.68
     hypert
    -0.66
     constitu
    -0.64
    dylib
    -0.64
    UGE
    -0.63
     veins
    -0.61
     Confederation
    -0.61
     tracts
    -0.61
    POSITIVE LOGITS
    hof
    0.76
    arie
    0.69
    owski
    0.68
    illard
    0.68
    itiveness
    0.68
    rama
    0.66
    iak
    0.64
    rules
    0.64
     chops
    0.64
    riot
    0.63
    Activations Density 0.183%

    No Known Activations