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. 15136
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating higher likelihood or probability

    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
    +0.08
    0.2%
    1993
    +0.08
    0.2%
    674
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1428
    +0.08
    0.03
    1475
    +0.08
    0.02
    116
    +0.08
    0.03
    Negative Logits
    mittances
    -0.72
     rumore
    -0.68
     Chinois
    -0.67
     Romains
    -0.66
     caratteri
    -0.66
     incess
    -0.63
     fumo
    -0.63
     Violon
    -0.63
     Cinéma
    -0.63
     cartier
    -0.62
    POSITIVE LOGITS
    <bos>
    0.87
     than
    0.73
    Than
    0.63
     než
    0.59
     Than
    0.58
     THAN
    0.57
    than
    0.56
     Likely
    0.50
     chance
    0.49
     likely
    0.48
    Activations Density 0.225%

    No Known Activations