© 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. 1832
    Prev
    Next
    INDEX
    Explanations

    terms related to the idea of "connecting the dots."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "connecting the dots" in discussions

    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
    inen
    -0.85
    obe
    -0.80
     detrim
    -0.71
    ods
    -0.69
    ģ
    -0.68
    İ
    -0.67
    âĶĢâĶĢâĶĢâĶĢ
    -0.66
    cler
    -0.66
    enum
    -0.66
    arily
    -0.66
    POSITIVE LOGITS
     dots
    0.91
    hyde
    0.86
    pend
    0.78
    ="#
    0.78
    hig
    0.73
    hov
    0.72
    burgh
    0.71
    dash
    0.71
    hole
    0.70
    ynthesis
    0.69
    Activations Density 0.023%

    No Known Activations