© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 285
    Prev
    Next
    INDEX
    Explanations

    words related to market share and market conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to market dynamics and competition

    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
     Lak
    -0.67
    sonian
    -0.66
     Mous
    -0.65
    uyomi
    -0.64
     Protective
    -0.64
     Kah
    -0.64
    uras
    -0.64
     Mountains
    -0.63
     Mub
    -0.63
     Biological
    -0.63
    POSITIVE LOGITS
    places
    1.48
    hare
    1.27
     share
    1.15
    eers
    1.09
    place
    1.05
    ability
    1.03
    share
    0.92
     penetration
    0.91
     saturation
    0.89
     stalls
    0.87
    Activations Density 0.043%

    No Known Activations