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. 23447
    Prev
    Next
    INDEX
    Explanations

    descriptions of creating or developing products or content

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to goals and objectives in various contexts

    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
    aired
    -0.72
    redo
    -0.67
    éĸ
    -0.62
    sis
    -0.62
    Fax
    -0.62
    rys
    -0.61
    soever
    -0.60
     Quit
    -0.59
    yang
    -0.59
    ©
    -0.58
    POSITIVE LOGITS
     simplicity
    1.02
     maximum
    0.92
     something
    0.91
     clarity
    0.91
     consistency
    0.87
     informative
    0.85
     maximal
    0.85
     concise
    0.84
     uniqueness
    0.84
     informational
    0.82
    Activations Density 0.313%

    No Known Activations