© 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. 13752
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions and settings

    oai_token-act-pair · gpt-3.5-turbo

    instances of character actions or movements within a narrative

    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
    NAS
    -0.79
    escription
    -0.76
    ancial
    -0.75
    thumbnails
    -0.73
     !!
    -0.73
    Ñĥ
    -0.72
     AMERICA
    -0.72
    Hamilton
    -0.72
    Miami
    -0.72
    !,
    -0.72
    POSITIVE LOGITS
     blonde
    1.21
     brun
    1.12
     parchment
    1.02
     blond
    1.02
     potion
    1.02
     crimson
    1.00
     goblin
    0.99
     girl
    0.99
     elf
    0.98
     Weasley
    0.96
    Activations Density 0.196%

    No Known Activations