© 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. 14380
    Prev
    Next
    INDEX
    Explanations

    phrases describing specific examples or instances within a broader category or context

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of "such as" followed by examples

    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
    ATIONAL
    -0.81
    /$
    -0.68
    20439
    -0.66
    ATH
    -0.66
    YD
    -0.64
    Cause
    -0.62
    YR
    -0.62
    Reply
    -0.62
    Girl
    -0.62
    ALSE
    -0.61
    POSITIVE LOGITS
    pired
    1.08
    pects
    0.91
     ours
    0.80
    piring
    0.79
    etheless
    0.78
    pires
    0.77
     evidenced
    0.77
    semb
    0.76
     regards
    0.75
    lihood
    0.73
    Activations Density 0.143%

    No Known Activations