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. 13463
    Prev
    Next
    INDEX
    Explanations

    quotes and opinions from various sources

    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
    1535
    +0.16
    0.5%
    2034
    +0.14
    0.4%
    872
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.16
    0.09
    1535
    +0.14
    0.08
    827
    +0.13
    0.07
    Negative Logits
     emphat
    -1.85
     affor
    -1.78
     increa
    -1.77
     viciss
    -1.75
     scrat
    -1.74
     encomp
    -1.71
     maneu
    -1.71
     indestru
    -1.68
     guarante
    -1.68
     lamborghini
    -1.67
    POSITIVE LOGITS
     He
    0.97
     he
    0.94
    He
    0.93
    ConverterFactory
    0.81
    he
    0.78
    UseVisualStyle
    0.76
     His
    0.74
     그는
    0.74
     он
    0.74
    ImageBackground
    0.73
    Activations Density 0.721%

    No Known Activations