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. 1354
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant political events and themes

    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
    +0.16
    0.5%
    1314
    +0.11
    0.3%
    1013
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.16
    0.06
    1870
    +0.11
    0.03
    62
    +0.10
    0.04
    Negative Logits
     affor
    -1.03
     impra
    -0.98
     scrat
    -0.95
     desir
    -0.93
     increa
    -0.93
     purcha
    -0.92
     suscep
    -0.92
     snoopy
    -0.91
     strick
    -0.90
     peppa
    -0.90
    POSITIVE LOGITS
     politics
    0.58
     antigu
    0.56
    })*/
    0.56
     culture
    0.56
     discourse
    0.55
     affairs
    0.55
     history
    0.54
     society
    0.54
    colazione
    0.51
    });*/
    0.50
    Activations Density 0.445%

    No Known Activations