© 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. 11296
    Prev
    Next
    INDEX
    Explanations

    phrases highlighting a standout or distinctive element

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to being part of a group or standing out from a crowd

    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
    nor
    -0.73
    wright
    -0.73
    Episode
    -0.70
    face
    -0.70
    ãĤ¬
    -0.69
    USE
    -0.68
    URE
    -0.67
    pose
    -0.66
    once
    -0.64
    hyde
    -0.64
    POSITIVE LOGITS
     plethora
    1.21
     myriad
    1.19
     multitude
    1.17
     clutter
    1.13
     ashes
    1.09
     bunch
    1.08
     ranks
    1.07
     rubble
    1.06
     wreckage
    1.06
     pile
    1.05
    Activations Density 0.219%

    No Known Activations