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. 1384
    Prev
    Next
    INDEX
    Explanations

    feedback or tips provided for improvement

    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
    2034
    +0.25
    0.9%
    1535
    +0.23
    0.8%
    382
    +0.20
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.25
    0.12
    1535
    +0.23
    0.09
    610
    +0.20
    0.07
    Negative Logits
    Lma
    -1.16
     sappi
    -1.16
    Ikr
    -1.07
    Lmfao
    -1.06
    Noice
    -1.06
    FTFY
    -1.04
     stihl
    -1.03
     uncin
    -1.03
     vogli
    -1.01
     gonz
    -1.01
    POSITIVE LOGITS
     Therefore
    0.80
    ↵↵
    0.78
     Whilst
    0.77
     Also
    0.76
     However
    0.75
     They
    0.74
     This
    0.73
    <eos>
    0.73
     Furthermore
    0.72
     Hence
    0.71
    Activations Density 0.489%

    No Known Activations