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. 11-RES-JB
    6. 10778
    Prev
    Next
    INDEX
    Explanations

    vertical bars symbol "|" and lowercase letters "l" in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    sections of text with a focus on formatting and structure markers

    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
    chenko
    -0.74
    anium
    -0.73
    ibly
    -0.72
    atem
    -0.71
    opian
    -0.70
    esi
    -0.69
    amen
    -0.68
    aband
    -0.68
    ory
    -0.67
    ixel
    -0.67
    POSITIVE LOGITS
    cffff
    1.01
     |--
    0.86
    ··
    0.83
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.82
    ————————
    0.81
     CrossRef
    0.81
     Contents
    0.80
     Difference
    0.78
    ¯¯¯¯¯¯¯¯
    0.78
    \\\\\\\\\\\\\\\\
    0.77
    Activations Density 0.028%

    No Known Activations