© 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. 6-RES-JB
    11. 5076
    Prev
    Next
    INDEX
    Explanations

    proper nouns, likely related to politics or government entities

    oai_token-act-pair · gpt-3.5-turbo

    trailing punctuation marks or unknown characters

    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
    jri
    -0.65
     destro
    -0.63
    iterranean
    -0.62
     reperto
    -0.61
    wcs
    -0.61
    wagon
    -0.59
     corrid
    -0.59
    oppy
    -0.59
    vertisement
    -0.57
     contrace
    -0.57
    POSITIVE LOGITS
    ITED
    0.60
     âĵĺ
    0.54
     HERO
    0.52
     Fired
    0.50
     Mars
    0.50
     Horror
    0.49
     Islam
    0.48
     Squirrel
    0.48
    IVES
    0.48
     Endless
    0.47
    Activations Density 0.156%

    No Known Activations