© 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. 8-RES-JB
    11. 11298
    Prev
    Next
    INDEX
    Explanations

    names related to a specific political figure (Kirchner)

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual and the concept of winning or losing streaks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ated
    -0.83
    ation
    -0.82
    ument
    -0.78
    ative
    -0.75
    aneous
    -0.74
    onomic
    -0.74
    aneously
    -0.74
    ractor
    -0.71
    uments
    -0.71
    ating
    -0.67
    POSITIVE LOGITS
    y
    1.18
    yu
    0.83
    isSpecialOrderable
    0.83
    irtual
    0.81
    yang
    0.77
    hold
    0.74
    yt
    0.72
    flake
    0.71
    iets
    0.71
    broken
    0.70
    Activations Density 0.079%

    No Known Activations