© 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. 4-RES-JB
    11. 15176
    Prev
    Next
    INDEX
    Explanations

    mentions of chapters, branches, and wings of different organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to organizational affiliations and their branches

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

    No Comments

    Negative Logits
    udeau
    -0.78
     mating
    -0.75
     Bagg
    -0.71
     puck
    -0.67
     injure
    -0.67
     kittens
    -0.65
     Ducks
    -0.65
    ipeg
    -0.64
     Cinderella
    -0.64
     collisions
    -0.63
    POSITIVE LOGITS
     dedicated
    0.80
    istries
    0.80
     specializing
    0.77
     affiliated
    0.76
     coordinating
    0.74
    lance
    0.73
    aires
    0.72
     headquartered
    0.72
    RECT
    0.71
    orate
    0.71
    Activations Density 0.157%

    No Known Activations