© 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. 9-RES-JB
    11. 23254
    Prev
    Next
    INDEX
    Explanations

    words related to objects or entities associated with physical sensations or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    descriptions of physical attributes or objects

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -1.05
    URA
    -0.94
    Contents
    -0.90
    Ĵ
    -0.90
    Saharan
    -0.89
    ¸
    -0.86
    ĺ
    -0.84
    Sche
    -0.82
    Sah
    -0.80
    Money
    -0.80
    POSITIVE LOGITS
     syndrome
    1.00
     salesman
    0.99
     soup
    0.91
     salute
    0.87
     fiasco
    0.82
     fallacy
    0.79
     sculpture
    0.78
     grin
    0.77
     fungus
    0.77
     massacre
    0.77
    Activations Density 0.411%

    No Known Activations