© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9496
    Prev
    Next
    INDEX
    Explanations

    contextual cues like sentence endings or structural elements such as quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and patterns related to dialogue or quoted speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =]
    -0.62
    idth
    -0.61
     watered
    -0.59
    userc
    -0.59
    iliated
    -0.58
    ãĤ¼ãĤ¦ãĤ¹
    -0.57
     designated
    -0.57
     disapprove
    -0.57
     antit
    -0.56
    aditional
    -0.56
    POSITIVE LOGITS
    Researchers
    0.80
    SPONSORED
    0.80
    Dur
    0.78
    Labour
    0.77
    RESULTS
    0.75
    Press
    0.75
    Students
    0.74
    Finally
    0.74
    Shape
    0.74
    ¶
    0.72
    Activations Density 0.886%

    No Known Activations