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. 9-RES-JB
    6. 158
    Prev
    Next
    INDEX
    Explanations

    descriptions related to visual aesthetics and design

    oai_token-act-pair · gpt-3.5-turbo

    descriptive elements related to visual style and emotional tone in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.77
     Brill
    -0.70
    ModLoader
    -0.68
    Dur
    -0.63
     Brut
    -0.63
     mathemat
    -0.63
    ccording
    -0.60
    dit
    -0.58
     horizont
    -0.58
    ©¶æ¥µ
    -0.57
    POSITIVE LOGITS
    anse
    0.61
    raft
    0.60
    and
    0.59
     li
    0.59
    ãĥ¼
    0.57
    abeth
    0.57
     q
    0.57
     gmaxwell
    0.56
    aru
    0.56
    etsu
    0.55
    Activations Density 0.127%

    No Known Activations