© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13690
    Prev
    Next
    INDEX
    Explanations

    mentions of "New Hampshire" in news articles

    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
    950
    +0.15
    0.6%
    1335
    +0.12
    0.4%
    1156
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.15
    0.03
    227
    +0.12
    0.04
    1335
    +0.12
    0.03
    Negative Logits
    <?
    
    -0.59
     accompagne
    -0.59
     ouvre
    -0.58
     exé
    -0.57
     remplace
    -0.55
    <?
    -0.55
     contribue
    -0.55
    Obrázky
    -0.53
     prouve
    -0.53
    
    
    -0.53
    POSITIVE LOGITS
     Maine
    0.97
     Vermont
    0.92
    Maine
    0.88
     Hampshire
    0.83
    Vermont
    0.83
     maine
    0.77
     NH
    0.72
     Dartmouth
    0.69
    pshire
    0.67
     ricardo
    0.59
    Activations Density 0.143%

    No Known Activations