Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14066
    Prev
    Next
    INDEX
    Explanations

    information related to a specific commercial establishment, possibly a fast-food restaurant

    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
    1013
    +0.14
    0.4%
    946
    +0.12
    0.4%
    1533
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.14
    0.07
    1050
    +0.12
    0.04
    1553
    +0.10
    0.06
    Negative Logits
     Mémoires
    -0.84
     Sinal
    -0.84
     Traité
    -0.83
     »>
    -0.80
     Augu
    -0.80
     Cæ
    -0.78
     Lettre
    -0.77
     Coim
    -0.77
     Lég
    -0.77
     §.
    -0.76
    POSITIVE LOGITS
    gonic
    0.71
     checkout
    0.61
     purchase
    0.59
    featureID
    0.58
     customer
    0.57
     shop
    0.56
     purchases
    0.55
     cashier
    0.55
     coupon
    0.54
     transaction
    0.53
    Activations Density 0.555%

    No Known Activations