© 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. 12-RES-JB
    11. 4313
    Prev
    Next
    INDEX
    Explanations

    personal possessions and actions associated with them, such as possessions and actions of an individual

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to eyes being closed and openness to new experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    hov
    -0.80
    CTV
    -0.69
    unk
    -0.67
    DI
    -0.66
    VICE
    -0.66
    ————
    -0.65
    ĺħ
    -0.62
    ESA
    -0.62
    alter
    -0.62
    anu
    -0.61
    POSITIVE LOGITS
     doors
    1.57
     door
    1.51
     gates
    1.34
     lid
    1.12
     Door
    1.11
     gate
    1.08
     Pandora
    1.08
    door
    1.07
     Doors
    1.07
     curtains
    1.06
    Activations Density 0.151%

    No Known Activations