© 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. 11-RES-JB
    11. 5140
    Prev
    Next
    INDEX
    Explanations

    dialogue with varied emotional and exclamation expressions

    oai_token-act-pair · gpt-3.5-turbo

    dialogues and conversational elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     individually
    -0.82
     independently
    -0.78
     contrasts
    -0.78
     incentives
    -0.76
     proportion
    -0.76
     separately
    -0.74
     amounts
    -0.73
     debates
    -0.73
     foreseeable
    -0.72
     underscores
    -0.71
    POSITIVE LOGITS
    Hello
    1.34
     Hello
    1.21
    Hi
    1.18
     hello
    1.16
    hello
    1.14
    Hey
    1.14
     Hey
    1.11
    Yo
    1.07
     hi
    1.07
     hey
    1.06
    Activations Density 0.194%

    No Known Activations