Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7945
    Prev
    Next
    INDEX
    Explanations

    terms related to riots and civil unrest

    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
    889
    +0.17
    0.7%
    241
    +0.15
    0.6%
    204
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.17
    0.03
    889
    +0.15
    0.03
    241
    +0.14
    0.04
    Negative Logits
    OGND
    -0.58
    StoreMessageInfo
    -0.53
    ตร์
    -0.52
    ագրություններ
    -0.51
    eleste
    -0.50
    andescent
    -0.49
    ğiniz
    -0.48
    ğimiz
    -0.46
    preso
    -0.45
     AspNetCore
    -0.44
    POSITIVE LOGITS
     ri
    1.10
     Ri
    1.08
    Ri
    1.00
     RI
    0.97
     Ril
    0.91
     quoique
    0.88
    ri
    0.86
     RIC
    0.83
     Riv
    0.82
     RIB
    0.82
    Activations Density 0.146%

    No Known Activations