© 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. 9063
    Prev
    Next
    INDEX
    Explanations

    lines or phrases denoting a specific boundary or limit

    oai_token-act-pair · gpt-3.5-turbo

    references to "lines" in various contexts

    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
    ricular
    -0.91
    ramid
    -0.73
    rontal
    -0.73
    è¦ļéĨĴ
    -0.71
    doms
    -0.71
    undai
    -0.70
    CLASSIFIED
    -0.70
    DOM
    -0.70
    KNOWN
    -0.68
    sburg
    -0.67
    POSITIVE LOGITS
    ages
    1.00
    lines
    0.98
    backer
    0.93
     line
    0.92
     lines
    0.89
    aments
    0.89
    line
    0.89
    breaks
    0.87
     Lines
    0.76
    ups
    0.74
    Activations Density 0.035%

    No Known Activations