Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9768
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and appreciation towards people or entities

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and appreciation

    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
    ãĤ¨ãĥ«
    -0.73
    rosso
    -0.70
    gur
    -0.70
     filler
    -0.68
     breakup
    -0.68
     balk
    -0.66
     dunno
    -0.66
    idges
    -0.65
    void
    -0.65
     boredom
    -0.64
    POSITIVE LOGITS
     our
    1.08
     Congressman
    1.00
     Governor
    0.97
     Senator
    0.96
     Members
    0.95
     Secretary
    0.92
     colleagues
    0.89
     Chairman
    0.89
     Attorney
    0.87
     Representative
    0.86
    Activations Density 0.413%

    No Known Activations