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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 10267
    Prev
    Next
    INDEX
    Explanations

    strings of text or characters within a document, especially those related to programming concepts and data formats

    oai_token-act-pair · gpt-3.5-turbo

    references to string data types and their characteristics in programming, especially in the context of UTF-8 encoding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndra
    -0.93
    arak
    -0.88
    involved
    -0.83
    gaard
    -0.81
    uckland
    -0.78
    armac
    -0.76
    stand
    -0.76
    agonists
    -0.76
    ilyn
    -0.75
    agonist
    -0.73
    POSITIVE LOGITS
     encoded
    1.09
     strings
    1.09
    UTF
    1.07
     encoding
    1.02
     UTF
    0.98
     literal
    0.97
     text
    0.97
     liter
    0.96
     ASCII
    0.95
     readable
    0.92
    Activations Density 0.106%

    No Known Activations