© 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. 1066
    Prev
    Next
    INDEX
    Explanations

    names of government officials or political figures

    oai_token-act-pair · gpt-3.5-turbo

    the letter 's' in various contexts

    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
    Reviewer
    -0.74
     Siber
    -0.68
    Compare
    -0.66
    mass
    -0.64
     Rothschild
    -0.62
    esp
    -0.62
    KT
    -0.61
    yz
    -0.60
    PUT
    -0.59
    OIL
    -0.59
    POSITIVE LOGITS
    ustainable
    0.90
    ullivan
    0.89
    ustain
    0.88
    wered
    0.87
    pecially
    0.85
    olutions
    0.85
    outhern
    0.84
    ources
    0.84
    olution
    0.81
    atisf
    0.81
    Activations Density 0.255%

    No Known Activations