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. 2865
    Prev
    Next
    INDEX
    Explanations

    objects or items that can be contained or stored in a box

    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
    478
    +0.09
    0.2%
    1842
    +0.08
    0.2%
    605
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1830
    +0.09
    0.03
    118
    +0.08
    0.04
    1167
    +0.08
    0.02
    Negative Logits
     suspic
    -0.91
     Haci
    -0.91
     Souha
    -0.88
     Keny
    -0.84
     utaf
    -0.81
     Juf
    -0.80
     philanth
    -0.79
     quoc
    -0.78
     maksi
    -0.78
     sophistic
    -0.78
    POSITIVE LOGITS
     all
    0.96
    all
    0.86
     everything
    0.85
     allemaal
    0.78
     alles
    0.75
    everything
    0.74
     tất
    0.72
     tudo
    0.71
     anything
    0.70
    etc
    0.70
    Activations Density 0.424%

    No Known Activations