© 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. 2-RES-JB
    11. 17655
    Prev
    Next
    INDEX
    Explanations

    appearances of the word "out"

    oai_token-act-pair · gpt-3.5-turbo

    references to being "out" or a state of being outside

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cius
    -0.73
    antry
    -0.72
    cious
    -0.69
     tyr
    -0.67
     arsen
    -0.65
    ingham
    -0.61
    avorite
    -0.60
    iosity
    -0.59
    etsk
    -0.58
     Pry
    -0.57
    POSITIVE LOGITS
    fitted
    1.07
    stretched
    1.01
    lier
    0.94
    posts
    0.90
    doors
    0.89
    casts
    0.86
    smart
    0.85
    wards
    0.84
    )=(
    0.83
    flows
    0.79
    Activations Density 0.154%

    No Known Activations