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. 8387
    Prev
    Next
    INDEX
    Explanations

    phrases related to beliefs and values, especially focusing on individual beliefs, societal values, and the juxtaposition of different beliefs and values

    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
    1870
    +0.10
    0.3%
    1265
    +0.10
    0.3%
    1926
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.10
    0.05
    136
    +0.10
    0.03
    1363
    +0.09
    0.04
    Negative Logits
     osal
    -0.83
     hcm
    -0.73
     rispond
    -0.69
     dovre
    -0.69
     encomp
    -0.69
     interro
    -0.69
     vogli
    -0.67
     ridu
    -0.67
     allarg
    -0.66
     pessi
    -0.65
    POSITIVE LOGITS
     beliefs
    0.81
    values
    0.62
     values
    0.60
     convictions
    0.57
    Values
    0.56
     EINVAL
    0.56
     thoughts
    0.56
     attitudes
    0.55
     principles
    0.55
    VALUES
    0.53
    Activations Density 0.327%

    No Known Activations