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. 15798
    Prev
    Next
    INDEX
    Explanations

    mentions of a person named Mary

    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
    1573
    +0.15
    0.6%
    866
    +0.14
    0.6%
    874
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1573
    +0.15
    0.02
    866
    +0.14
    0.02
    874
    +0.14
    0.02
    Negative Logits
    judice
    -0.53
    PARATUS
    -0.51
    PONENTS
    -0.49
    strictEqual
    -0.49
     marginBottom
    -0.49
     ка
    -0.47
    PARED
    -0.46
    ']}
    -0.46
    ROLLER
    -0.46
    전
    -0.46
    POSITIVE LOGITS
     Mary
    1.38
     MARY
    1.36
     mary
    1.36
     Traité
    1.33
    Mary
    1.32
     Chapitre
    1.26
     simplif
    1.21
    MARY
    1.20
     salomon
    1.07
     Souha
    1.05
    Activations Density 0.073%

    No Known Activations