© 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. 16846
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations or institutions

    oai_token-act-pair · gpt-3.5-turbo

    names of research institutions, projects, awards, and trusts associated with various fields

    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
    umbers
    -0.72
    dated
    -0.69
    ierrez
    -0.69
    fitting
    -0.68
    iable
    -0.67
    inventoryQuantity
    -0.67
    iability
    -0.65
    theless
    -0.65
     directions
    -0.64
    ardless
    -0.63
    POSITIVE LOGITS
     Initiative
    0.90
     Collection
    0.90
     Cooperative
    0.89
    naire
    0.87
     Ltd
    0.82
     Consortium
    0.82
     Prize
    0.81
     Scholarship
    0.81
     School
    0.81
     Foundation
    0.80
    Activations Density 0.238%

    No Known Activations