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. 8241
    Prev
    Next
    INDEX
    Explanations

    questions about ethics and morality, especially related to societal and political circumstances

    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
    2034
    +0.17
    0.5%
    197
    +0.11
    0.3%
    674
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.17
    0.05
    118
    +0.11
    0.05
    610
    +0.10
    0.04
    Negative Logits
     uncin
    -0.76
     solidar
    -0.70
     notor
    -0.68
     platt
    -0.65
    Wię
    -0.65
     ideolog
    -0.65
     dises
    -0.64
     tomat
    -0.63
     robus
    -0.63
    Warto
    -0.62
    POSITIVE LOGITS
     $?
    0.76
     déploy
    0.73
     écout
    0.71
     prêtres
    0.70
     Juifs
    0.65
     chrétien
    0.64
     dédi
    0.64
    ?
    0.64
     lumineuse
    0.63
     yoksa
    0.63
    Activations Density 0.165%

    No Known Activations