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. 1781
    Prev
    Next
    INDEX
    Explanations

    information related to financial and economic crises, government policies, and social issues

    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
    1919
    +0.11
    0.3%
    1978
    +0.11
    0.3%
    581
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2045
    +0.11
    0.06
    862
    +0.11
    0.03
    1919
    +0.11
    0.05
    Negative Logits
     incess
    -1.19
     ordina
    -1.05
     universale
    -1.03
     mef
    -1.00
     spirituale
    -0.98
     ananas
    -0.98
     cioc
    -0.95
     utop
    -0.93
     poliester
    -0.93
     peculi
    -0.92
    POSITIVE LOGITS
     have
    0.77
     are
    0.76
     had
    0.72
     were
    0.72
     went
    0.71
     came
    0.69
     belonged
    0.65
     has
    0.65
     underwent
    0.63
     surveyed
    0.63
    Activations Density 0.359%

    No Known Activations