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. 328
    Prev
    Next
    INDEX
    Explanations

    terms related to names and specific locations

    oai_token-act-pair · gpt-3.5-turbo

    prominent names or terms associated with specific events or contexts

    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
     Stellar
    -0.78
    ModLoader
    -0.77
    lihood
    -0.75
    Const
    -0.71
     Trin
    -0.70
     Synd
    -0.70
     gobl
    -0.69
     Syndicate
    -0.69
    ¥ŀ
    -0.68
    ãĥ¼ãĥĨ
    -0.68
    POSITIVE LOGITS
    ay
    1.28
    ays
    1.27
    AY
    1.24
    aya
    1.10
    aw
    1.03
    aign
    1.00
    awn
    0.97
    ayan
    0.96
    ah
    0.96
    aye
    0.93
    Activations Density 0.251%

    No Known Activations