© 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. 11-RES-JB
    11. 13233
    Prev
    Next
    INDEX
    Explanations

    mentions related to legal or administrative documents

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or regulatory issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    DOM
    -0.87
    VM
    -0.83
     Yas
    -0.76
     Uriel
    -0.75
    û
    -0.73
    sem
    -0.73
    Mah
    -0.69
    falls
    -0.68
     Yosemite
    -0.68
     DOM
    -0.66
    POSITIVE LOGITS
    Co
    2.23
     Cooper
    2.16
     Co
    2.14
    co
    1.89
     Cooke
    1.71
     CO
    1.67
    CO
    1.67
     co
    1.63
     Cohen
    1.57
     Cooperative
    1.47
    Activations Density 0.256%

    No Known Activations