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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 1689
    Prev
    Next
    INDEX
    Explanations

    terms related to specific events or topics across a variety of contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social issues and community events

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

    No Comments

    Negative Logits
    )."
    -0.86
    ]."
    -0.79
    ).[
    -0.73
    }.
    -0.73
    )).
    -0.70
    é¾įå
    -0.69
    anwhile
    -0.67
     latter
    -0.67
    %).
    -0.66
     respectively
    -0.63
    POSITIVE LOGITS
    20439
    0.57
     puzz
    0.57
    undrum
    0.55
    htaking
    0.52
    reetings
    0.51
    outine
    0.51
    ="#
    0.50
     (#
    0.50
    avorite
    0.49
     sear
    0.48
    Activations Density 1.605%

    No Known Activations