© 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. 1-RES-JB
    11. 6687
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or activities being carried out by someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the concept of "getting out" or "being out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cius
    -0.79
    antry
    -0.74
    cious
    -0.69
     arsen
    -0.60
     mathemat
    -0.58
     tyr
    -0.57
    oshop
    -0.57
    etsk
    -0.56
    avorite
    -0.56
     laureate
    -0.56
    POSITIVE LOGITS
    fitted
    1.00
    stretched
    0.86
    posts
    0.84
    lier
    0.81
    )=(
    0.80
    wards
    0.77
    doors
    0.77
    casts
    0.77
    smart
    0.75
    flows
    0.73
    Activations Density 0.127%

    No Known Activations