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. 15581
    Prev
    Next
    INDEX
    Explanations

    dates in the format of year

    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
    478
    +0.15
    0.5%
    1699
    +0.14
    0.4%
    1535
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.15
    0.07
    1533
    +0.14
    0.05
    1079
    +0.12
    0.04
    Negative Logits
    Przyp
    -0.83
    Jakie
    -0.82
    Podob
    -0.79
    danke
    -0.77
    Gdzie
    -0.77
    nasel
    -0.77
    Zdra
    -0.75
    Dlaczego
    -0.74
    Kiedy
    -0.72
    Jeden
    -0.72
    POSITIVE LOGITS
     alkoh
    1.47
     silikon
    1.41
     allarg
    1.29
     kön
    1.28
    (%)
    1.28
     vasi
    1.28
     makro
    1.27
     pól
    1.26
     kollek
    1.25
     keramik
    1.23
    Activations Density 0.183%

    No Known Activations