© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14490
    Prev
    Next
    INDEX
    Explanations

    phrases indicating harmful situations or potential harm

    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
    674
    +0.12
    0.3%
    1978
    +0.10
    0.3%
    764
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.12
    0.03
    1849
    +0.10
    0.02
    488
    +0.09
    0.04
    Negative Logits
     Varan
    -0.58
     Hez
    -0.55
     Nema
    -0.55
     Momb
    -0.54
     Hald
    -0.54
     Gaut
    -0.54
     Hannes
    -0.51
     Albu
    -0.50
     Verder
    -0.50
     Middel
    -0.50
    POSITIVE LOGITS
     similar
    0.99
     similarly
    0.98
    similar
    0.97
    Similar
    0.88
     SIMILAR
    0.87
     similares
    0.85
     Similar
    0.81
    same
    0.72
     semelhante
    0.71
     hason
    0.68
    Activations Density 0.458%

    No Known Activations