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. 15092
    Prev
    Next
    INDEX
    Explanations

    references to file management instructions, especially those involving data backup and directory creation

    oai_token-act-pair · gpt-3.5-turbo

    references to the second person pronoun "your."

    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
    abl
    -0.77
    hig
    -0.76
    vous
    -0.74
    amar
    -0.70
    ttes
    -0.70
    Õ
    -0.69
    worth
    -0.69
    neg
    -0.69
    perse
    -0.68
    ËĪ
    -0.68
    POSITIVE LOGITS
     own
    1.42
     favourite
    1.41
     favorite
    1.39
     existing
    1.05
     desired
    1.04
     preferred
    1.04
     chosen
    0.95
     favorites
    0.94
     opponent
    0.93
     workspace
    0.91
    Activations Density 0.108%

    No Known Activations