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

    Neuronpedia

    APICircuit 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. 6-RES-JB
    6. 11367
    Prev
    Next
    INDEX
    Explanations

    Unicode characters that are often used as visual representations of emotions or actions, such as arrows or symbols

    oai_token-act-pair · gpt-3.5-turbo

    instances of the symbol "ľ," indicating a focus on specific typography or formatting issues

    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
     apes
    -0.71
     condem
    -0.71
     Patriarch
    -0.71
     Norn
    -0.69
     clitor
    -0.68
     mounts
    -0.68
     reflex
    -0.67
     primates
    -0.67
     telesc
    -0.66
     clones
    -0.65
    POSITIVE LOGITS
    ï¸ı
    1.10
    uthor
    0.94
    âĶĢâĶĢ
    0.91
    ternity
    0.91
    \-
    0.86
    ACP
    0.84
    oil
    0.83
    vernment
    0.81
    âĸł
    0.80
    lean
    0.80
    Activations Density 0.231%

    No Known Activations