© 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 EvalsExportsAPI 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. 8500
    Prev
    Next
    INDEX
    Explanations

    entities or actions related to people and their roles in various scenarios

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups involved in specific actions or roles

    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
    00007
    -0.75
    quet
    -0.73
    EMBER
    -0.68
    requires
    -0.67
    hess
    -0.67
    =\"
    -0.66
    roxy
    -0.65
    rather
    -0.65
    quez
    -0.65
    anship
    -0.63
    POSITIVE LOGITS
     aren
    0.73
     constitute
    0.73
     are
    0.72
     comprise
    0.72
     were
    0.70
     weren
    0.70
     respective
    0.68
     arsen
    0.66
     composing
    0.66
     carry
    0.63
    Activations Density 0.370%

    No Known Activations