© 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. 12-RES-JB
    11. 2791
    Prev
    Next
    INDEX
    Explanations

    comparisons indicating superiority or inferiority

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    comparative phrases and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igious
    -0.80
    erity
    -0.78
    few
    -0.69
    ciplinary
    -0.64
    istries
    -0.64
    anship
    -0.63
    illions
    -0.62
    ancial
    -0.62
    agonists
    -0.61
    virt
    -0.60
    POSITIVE LOGITS
     usual
    1.31
     normal
    1.10
     before
    1.09
     expected
    1.06
     previous
    0.98
     advertised
    0.97
    expected
    0.96
    usual
    0.96
    before
    0.94
     last
    0.90
    Activations Density 0.257%

    No Known Activations