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. 1448
    Prev
    Next
    INDEX
    Explanations

    anatomical terms related to injuries or violence

    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
    1385
    +0.14
    0.4%
    1317
    +0.12
    0.3%
    1013
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1317
    +0.14
    0.05
    1907
    +0.12
    0.04
    402
    +0.11
    0.04
    Negative Logits
     Settembre
    -1.19
     Ottobre
    -1.09
     Luglio
    -0.99
     autunno
    -0.94
     sappi
    -0.87
     Giugno
    -0.86
     soggior
    -0.84
     affez
    -0.84
     ordina
    -0.83
     interessa
    -0.83
    POSITIVE LOGITS
     McInt
    0.76
     McLaugh
    0.69
     while
    0.61
     during
    0.56
     Cuth
    0.54
     and
    0.53
     whilst
    0.51
     testData
    0.51
    .
    0.51
     Při
    0.50
    Activations Density 0.184%

    No Known Activations