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. 15148
    Prev
    Next
    INDEX
    Explanations

    mentions of the brand "Red Bull"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the brand "Red Bull."

    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
    tackle
    -0.81
    agara
    -0.74
    selection
    -0.72
    bats
    -0.69
    ãĥ£
    -0.69
    apore
    -0.67
     Cth
    -0.67
    went
    -0.66
    recomm
    -0.66
    matter
    -0.64
    POSITIVE LOGITS
     Shooter
    0.91
     Chili
    0.81
     Arcade
    0.75
     Networks
    0.74
     Armory
    0.72
     Reloaded
    0.72
     Industries
    0.70
    ©¶æ
    0.69
    IDA
    0.67
     Revival
    0.67
    Activations Density 0.174%

    No Known Activations