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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 20216
    Prev
    Next
    INDEX
    Explanations

    words related to borrowing or names including "Lor"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of specific names and references to boredom

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ted
    -0.88
    eers
    -0.78
    ulate
    -0.77
    ilus
    -0.77
    hered
    -0.76
    paio
    -0.75
    cius
    -0.75
    ulates
    -0.73
    erate
    -0.72
    ichick
    -0.71
    POSITIVE LOGITS
    hood
    0.79
    ussia
    0.73
    iculture
    0.70
    atively
    0.69
    atives
    0.68
    OUGH
    0.68
    UST
    0.68
    asta
    0.68
    ingo
    0.67
     Adin
    0.64
    Activations Density 0.090%

    No Known Activations