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. 13536
    Prev
    Next
    INDEX
    Explanations

    statements about political or military actions and events

    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
    1741
    +0.13
    0.4%
    2019
    +0.13
    0.4%
    1445
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.13
    0.05
    1162
    +0.13
    0.04
    1265
    +0.12
    0.04
    Negative Logits
     étend
    -1.07
     prétend
    -1.06
     bonté
    -1.05
     réal
    -1.03
     renfer
    -1.03
     Outils
    -1.02
     prédé
    -1.02
     rafra
    -1.01
     Décembre
    -1.01
     sappi
    -1.01
    POSITIVE LOGITS
     finding
    0.63
     we
    0.61
     there
    0.60
     perhaps
    0.57
     attention
    0.57
     opportunities
    0.55
     hopefully
    0.55
     many
    0.55
     questions
    0.54
     it
    0.54
    Activations Density 0.282%

    No Known Activations