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. 447
    Prev
    Next
    INDEX
    Explanations

    concepts or discussions related to theories and political ideologies, particularly focusing on the redistribution of resources and governance

    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
    1705
    +0.15
    0.6%
    1133
    +0.13
    0.5%
    1335
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.15
    0.04
    1133
    +0.13
    0.03
    203
    +0.11
    0.03
    Negative Logits
     Wiking
    -0.66
     Zeits
    -0.60
     Mathem
    -0.56
     glan
    -0.55
     Departement
    -0.55
     bayern
    -0.53
     kram
    -0.52
     Krim
    -0.52
     Reden
    -0.52
     fatale
    -0.52
    POSITIVE LOGITS
     theory
    1.09
    theory
    1.02
     theories
    1.00
    Theory
    0.98
     Theory
    0.95
     THEORY
    0.88
     Theories
    0.84
    THEORY
    0.77
     theor
    0.75
     zove
    0.71
    Activations Density 0.080%

    No Known Activations