© 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. 10-RES-JB
    11. 5747
    Prev
    Next
    INDEX
    Explanations

    direct speech dialogues enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    conversational quotes or dialogue in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     satell
    -0.95
     pole
    -0.86
    ¥ŀ
    -0.84
     adjud
    -0.81
     prospect
    -0.79
     foreseeable
    -0.79
     previously
    -0.78
     innov
    -0.78
     timely
    -0.78
     cycl
    -0.78
    POSITIVE LOGITS
    Yeah
    1.89
    Oh
    1.87
    Huh
    1.81
    Uh
    1.81
    Okay
    1.78
    Hmm
    1.76
    Alright
    1.74
    Well
    1.73
    Fuck
    1.71
    Yes
    1.71
    Activations Density 0.120%

    No Known Activations