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. 8283
    Prev
    Next
    INDEX
    Explanations

    references to media competition and rankings

    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
    198
    +0.13
    0.4%
    752
    +0.09
    0.2%
    692
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.13
    0.05
    1885
    +0.09
    0.04
    529
    +0.08
    0.05
    Negative Logits
    (":");
    -0.59
    eclamp
    -0.48
    uksessa
    -0.47
    deleteUser
    -0.47
    LogUtils
    -0.46
    assertIs
    -0.46
    MENAFN
    -0.45
    loginUser
    -0.45
    Thông
    -0.44
    ("."
    -0.43
    POSITIVE LOGITS
     competitors
    0.92
     competitor
    0.92
     rivals
    0.84
     Competitors
    0.84
     rival
    0.84
     riva
    0.78
     Ueb
    0.74
     competing
    0.70
     Campionato
    0.68
     voisin
    0.67
    Activations Density 0.455%

    No Known Activations