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. 755
    Prev
    Next
    INDEX
    Explanations

    references to corruption, scandal, bribery, and legal trouble involving high-ranking officials

    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
    604
    +0.12
    0.3%
    1177
    +0.10
    0.3%
    1445
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1593
    +0.12
    0.05
    1629
    +0.10
    0.03
    1364
    +0.10
    0.04
    Negative Logits
     thermomix
    -0.70
     tricot
    -0.68
     nutella
    -0.65
     broderie
    -0.65
     frambo
    -0.64
     fluo
    -0.64
    <bos>
    -0.63
     bonbons
    -0.63
     embodi
    -0.60
     eiffel
    -0.59
    POSITIVE LOGITS
     Punj
    0.64
     KPK
    0.61
     corruption
    0.61
    İstinadlar
    0.58
     bribery
    0.57
     semblable
    0.56
     scandal
    0.55
     Jä
    0.54
     Southwark
    0.54
     allegations
    0.54
    Activations Density 0.708%

    No Known Activations