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. 17849
    Prev
    Next
    INDEX
    Explanations

    descriptions of visual and artistic elements, with a focus on process and transparency

    oai_token-act-pair · gpt-3.5-turbo

    references to artistic elements and their characteristics

    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
    BSD
    -0.81
    ©¶æ¥µ
    -0.80
    ilk
    -0.76
    vernment
    -0.74
    Downloadha
    -0.74
     Ranked
    -0.73
    paid
    -0.72
    chool
    -0.71
    cancer
    -0.71
    nesty
    -0.70
    POSITIVE LOGITS
     motif
    1.58
     symbolism
    1.52
     imagery
    1.51
     meanings
    1.44
     themes
    1.40
     metaphors
    1.40
     juxtap
    1.40
     nuance
    1.38
     emotion
    1.37
     narrative
    1.35
    Activations Density 0.348%

    No Known Activations