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. 13951
    Prev
    Next
    INDEX
    Explanations

    explanations or descriptions

    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
    699
    +0.17
    0.6%
    397
    +0.15
    0.6%
    31
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.17
    0.06
    397
    +0.15
    0.04
    31
    +0.14
    0.04
    Negative Logits
     maksi
    -0.82
     seksi
    -0.80
     silikon
    -0.80
     kado
    -0.79
     keramik
    -0.76
     akut
    -0.76
     kafe
    -0.74
     lele
    -0.73
     krim
    -0.73
     tomat
    -0.72
    POSITIVE LOGITS
     explain
    1.17
     explanations
    1.05
     explanation
    1.04
     explaining
    1.02
    Explain
    1.01
     Explain
    1.01
     explains
    1.00
    explain
    0.98
     explained
    0.97
     why
    0.83
    Activations Density 0.109%

    No Known Activations