© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RES-JB
    11. 9611
    Prev
    Next
    INDEX
    Explanations

    organizations or departments related to law enforcement and government agencies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vo
    -0.64
    ¬¼
    -0.62
    andowski
    -0.61
    ģĸ
    -0.60
    ally
    -0.55
     fres
    -0.55
    worldly
    -0.55
     âĵĺ
    -0.53
     recapt
    -0.52
    Į
    -0.52
    POSITIVE LOGITS
     albeit
    0.90
     namely
    0.82
     including
    0.77
    Balt
    0.77
    DragonMagazine
    0.75
    Magikarp
    0.73
     however
    0.72
    anwhile
    0.72
     srf
    0.71
     but
    0.67
    Activations Density 0.358%

    No Known Activations