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. 14974
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names, especially related to gaming, sports, and politics

    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
    1272
    +0.13
    0.5%
    144
    +0.12
    0.5%
    1565
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1565
    +0.13
    0.06
    1272
    +0.12
    0.06
    144
    +0.12
    0.05
    Negative Logits
    Gdy
    -0.58
    <bos>
    -0.47
    Przyp
    -0.45
     borderRadius
    -0.43
     Jednak
    -0.43
    Dlaczego
    -0.43
     Ostat
    -0.42
     Dlatego
    -0.41
    Jakie
    -0.41
    NewUrlParser
    -0.40
    POSITIVE LOGITS
     Moderato
    0.88
     marte
    0.86
     swarovski
    0.85
     pican
    0.85
     broderie
    0.82
     fernando
    0.82
     Allegretto
    0.81
     milano
    0.80
     aquarelle
    0.80
     lapto
    0.80
    Activations Density 0.653%

    No Known Activations