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. 15622
    Prev
    Next
    INDEX
    Explanations

    sentences describing futuristic technological advancements

    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
    1937
    +0.13
    0.4%
    82
    +0.11
    0.4%
    62
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.13
    0.03
    1937
    +0.11
    0.04
    82
    +0.11
    0.03
    Negative Logits
     prétend
    -0.92
     viendra
    -0.88
     accompagne
    -0.86
     venait
    -0.83
     exé
    -0.82
     prendra
    -0.81
     soigne
    -0.81
     reconnaît
    -0.79
     jette
    -0.78
     entraîne
    -0.78
    POSITIVE LOGITS
    createTextNode
    0.58
     twofold
    0.51
    లాలు
    0.48
     is
    0.47
    ítmény
    0.47
     basically
    0.46
     useParams
    0.43
     simpel
    0.42
     voleva
    0.42
     actually
    0.42
    Activations Density 0.129%

    No Known Activations