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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19091
    Prev
    Next
    INDEX
    Explanations

    mentions of training programs for various professions, including police officers, soldiers, youth, magicians, and dolphins

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "train" and its variations used in various contexts related to training individuals or animals

    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´
    -0.67
    Ĥİ
    -0.67
    ãĤ©
    -0.63
    ffee
    -0.63
    rh
    -0.62
    Allen
    -0.59
    bum
    -0.58
    dot
    -0.58
     goodbye
    -0.58
    -----------
    -0.58
    POSITIVE LOGITS
     instructors
    0.91
     professionals
    0.90
     trainers
    0.88
     pilots
    0.86
     apprentices
    0.86
     athletes
    0.83
     technicians
    0.80
     extensively
    0.79
     manuals
    0.78
     techniques
    0.77
    Activations Density 0.078%

    No Known Activations