© 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. 3-RES-JB
    11. 23602
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific industries or areas of focus, such as food processing facilities or solar plants

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to health, environmental issues, and community structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įå
    -0.83
    $.
    -0.81
    )."
    -0.70
    )).
    -0.69
     eternity
    -0.69
    ]."
    -0.67
    EStreamFrame
    -0.67
    }.
    -0.63
    ãĤĭ
    -0.60
     sidx
    -0.59
    POSITIVE LOGITS
     consists
    0.74
    urches
    0.63
    undrum
    0.63
     teamed
    0.60
     consisted
    0.60
     debuted
    0.60
     has
    0.58
    ariat
    0.58
     relies
    0.57
     comprises
    0.57
    Activations Density 1.836%

    No Known Activations