© 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. 9373
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    patterns of letters or sequences resembling abbreviations or acronyms

    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
     Mehran
    -0.68
    vous
    -0.66
     whe
    -0.61
     Haram
    -0.60
    =""
    -0.60
    apt
    -0.59
    ifer
    -0.59
    VIDIA
    -0.58
    izu
    -0.58
    opard
    -0.57
    POSITIVE LOGITS
    side
    1.00
    pole
    0.87
    views
    0.85
    builders
    0.84
    view
    0.83
    holders
    0.83
     hopping
    0.80
     divid
    0.77
    iers
    0.75
    door
    0.74
    Activations Density 0.226%

    No Known Activations