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 · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14983
    Prev
    Next
    INDEX
    Explanations

    information about companies, such as their ownership, corporate structure, and financial activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    227
    +0.17
    0.5%
    198
    +0.14
    0.4%
    1445
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.17
    0.09
    1445
    +0.14
    0.08
    455
    +0.13
    0.01
    Negative Logits
     ftu
    -0.82
     foon
    -0.81
     zyn
    -0.79
     paff
    -0.77
     meis
    -0.76
     poff
    -0.74
     fup
    -0.74
     feen
    -0.73
     levis
    -0.72
     mef
    -0.72
    POSITIVE LOGITS
     headquartered
    0.86
     corporation
    0.75
     company
    0.75
     subsidiaries
    0.73
     companies
    0.66
     corporations
    0.64
     corporate
    0.64
     Company
    0.63
     Founded
    0.63
    quartered
    0.63
    Activations Density 0.880%

    No Known Activations