© 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. 1070
    Prev
    Next
    INDEX
    Explanations

    Russian text containing special characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    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
    xus
    -0.88
     deaf
    -0.84
     Hole
    -0.72
    warm
    -0.68
    fruit
    -0.68
     Sapphire
    -0.66
     tremend
    -0.65
    kefeller
    -0.64
     satell
    -0.64
    enei
    -0.64
    POSITIVE LOGITS
    enance
    1.04
    ÑĢ
    1.02
    оÐ
    1.00
    Ñĥ
    0.92
    о
    0.86
    а
    0.85
    л
    0.85
    riad
    0.84
    tal
    0.80
    rito
    0.80
    Activations Density 0.019%

    No Known Activations