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. 15597
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of detention, particularly indefinite detention and its effects

    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
    313
    +0.13
    0.4%
    1328
    +0.12
    0.4%
    1323
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1425
    +0.13
    0.02
    1323
    +0.12
    0.02
    313
    +0.12
    0.02
    Negative Logits
     affor
    -0.64
     scrat
    -0.63
     intersper
    -0.62
     apportion
    -0.60
     alre
    -0.59
     sophie
    -0.58
     purcha
    -0.57
     purch
    -0.55
     ugg
    -0.55
     olivia
    -0.55
    POSITIVE LOGITS
     detention
    1.06
     Detention
    0.94
     detained
    0.86
     detainees
    0.80
     deten
    0.74
     detain
    0.69
     detergente
    0.58
     custody
    0.58
     cuenca
    0.56
    ention
    0.56
    Activations Density 0.066%

    No Known Activations