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. 753
    Prev
    Next
    INDEX
    Explanations

    titles or roles related to leadership or management positions

    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
    316
    +0.14
    0.5%
    1870
    +0.14
    0.5%
    1637
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.14
    0.03
    1637
    +0.14
    0.03
    1110
    +0.11
    0.02
    Negative Logits
    coration
    -0.50
     ambassade
    -0.47
    南海
    -0.42
    řevě
    -0.41
    říve
    -0.40
     fundamentos
    -0.40
    πομπ
    -0.40
    řev
    -0.40
    舷
    -0.40
    ConstraintMaker
    -0.40
    POSITIVE LOGITS
     director
    1.30
     Director
    1.24
    director
    1.23
     directors
    1.18
    Director
    1.15
     Directors
    1.12
    directors
    1.10
     DIRECTOR
    1.09
    Directors
    1.01
    DIRECTOR
    0.98
    Activations Density 0.074%

    No Known Activations