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. 21089
    Prev
    Next
    INDEX
    Explanations

    mentions of franchises or specific entities across different categories such as plants, languages, bands, and games

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to franchises or series

    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
    ħĭ
    -0.75
    "]=>
    -0.72
    hash
    -0.69
    ĪĴ
    -0.63
    =#
    -0.63
    amaz
    -0.62
    pps
    -0.62
    ase
    -0.62
     Moines
    -0.61
    dds
    -0.59
    POSITIVE LOGITS
     consisting
    1.21
     comprising
    1.12
     encomp
    1.05
     primarily
    1.03
     principally
    1.01
     specializing
    1.00
     headquartered
    0.98
     featuring
    0.98
     comprised
    0.97
     although
    0.96
    Activations Density 0.323%

    No Known Activations