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. 0-RES-JB
    6. 21935
    Prev
    Next
    INDEX
    Explanations

    web-related terms and links within text

    oai_token-act-pair · gpt-3.5-turbo

    the registered trademark symbol (®)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tribe
    -0.73
    bors
    -0.70
    SPONSORED
    -0.67
    Living
    -0.65
    worker
    -0.65
    iki
    -0.60
     Native
    -0.60
     Tribal
    -0.60
    ikes
    -0.59
     wrestler
    -0.58
    POSITIVE LOGITS
     ®
    4.23
    UX
    1.24
    Ħ¢
    1.10
     âĸł
    1.10
     µ
    1.01
    ammers
    0.97
     guessing
    0.96
    ARDIS
    0.94
     Clara
    0.89
    olen
    0.89
    Activations Density 0.036%

    No Known Activations