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. 13557
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific topic or field, specifically focusing on computer science, programming, and possibly video game updates

    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
    1778
    +0.15
    0.6%
    990
    +0.14
    0.6%
    1068
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1778
    +0.15
    0.03
    990
    +0.14
    0.02
    325
    +0.12
    0.02
    Negative Logits
     Wray
    -0.49
     Blackstone
    -0.46
     Lud
    -0.45
     autoradio
    -0.45
    Crom
    -0.43
    Incidence
    -0.43
    Quantification
    -0.42
    Incon
    -0.40
     Mitochondrial
    -0.40
    Mitochond
    -0.40
    POSITIVE LOGITS
     Dep
    1.03
    Dep
    0.97
    dep
    0.92
     dep
    0.89
     DEP
    0.85
    DEP
    0.83
     Dép
    0.79
     deputies
    0.78
     Deportivo
    0.76
     deputy
    0.76
    Activations Density 0.078%

    No Known Activations