© 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. 3574
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and data manipulation, especially focusing on functions or concepts with the word "gener" or "Gener" in them

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

    references to generative processes or tools

    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
     deliberations
    -0.67
     pupil
    -0.65
     Heller
    -0.61
     waivers
    -0.61
    ĺħ
    -0.60
    WARE
    -0.60
     disciplinary
    -0.60
    LET
    -0.59
     vengeance
    -0.56
     Madison
    -0.56
    POSITIVE LOGITS
    osity
    1.59
    ics
    1.30
    ators
    1.22
    ically
    1.21
    ously
    1.17
    ational
    1.17
    ative
    1.16
    ating
    1.11
    icity
    1.10
    ous
    1.10
    Activations Density 0.028%

    No Known Activations