© 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. 20770
    Prev
    Next
    INDEX
    Explanations

    phrases related to machines, engineering, or industrial processes

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Machado" in various contexts

    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
    0000000000000000
    -0.71
    SHIP
    -0.66
     ast
    -0.64
     Vive
    -0.63
    Rush
    -0.63
    ential
    -0.60
     witness
    -0.58
     matter
    -0.57
     critically
    -0.56
     sheer
    -0.56
    POSITIVE LOGITS
    inery
    1.46
    ineries
    1.26
    inations
    1.17
    ismo
    1.04
    ining
    1.01
    insk
    1.01
    ined
    0.99
    otom
    0.95
    ufact
    0.90
    inas
    0.88
    Activations Density 0.046%

    No Known Activations