© 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. 9-RES-JB
    11. 20862
    Prev
    Next
    INDEX
    Explanations

    quotes or direct speech in the form of a conversation

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks used in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pole
    -0.85
     adjud
    -0.78
     valued
    -0.76
     characterized
    -0.75
     accident
    -0.74
     seasoned
    -0.73
     targeted
    -0.73
     foreseeable
    -0.73
     innov
    -0.73
     previously
    -0.72
    POSITIVE LOGITS
    Yeah
    1.81
    Oh
    1.70
    Huh
    1.70
    Hmm
    1.67
    Uh
    1.67
    Yes
    1.65
    Alright
    1.64
    Okay
    1.64
    Hey
    1.63
    Fuck
    1.57
    Activations Density 0.101%

    No Known Activations