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. 2951
    Prev
    Next
    INDEX
    Explanations

    phrases related to political protests and legal proceedings

    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
    198
    +0.14
    0.4%
    1177
    +0.12
    0.4%
    776
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.14
    0.08
    198
    +0.12
    0.06
    609
    +0.12
    0.05
    Negative Logits
     useCallback
    -0.76
     createContext
    -0.71
     insuffisamment
    -0.69
     useRef
    -0.64
    renza
    -0.59
    ofern
    -0.59
     ModelRenderer
    -0.59
     otomatig
    -0.58
    <bos>
    -0.57
    woor
    -0.56
    POSITIVE LOGITS
     Juf
    1.16
     unlaw
    1.14
     McLaugh
    1.14
     Confu
    1.11
     reluct
    1.10
     apprehen
    1.09
     depic
    1.04
     disagre
    1.02
     encomp
    1.01
     Bartholo
    1.00
    Activations Density 0.387%

    No Known Activations