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. 8247
    Prev
    Next
    INDEX
    Explanations

    mentions of specific ages or age-related information

    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
    1059
    +0.12
    0.4%
    871
    +0.12
    0.4%
    390
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1059
    +0.12
    0.03
    871
    +0.12
    0.03
    390
    +0.11
    0.03
    Negative Logits
     Noviembre
    -0.49
    derdag
    -0.47
     kelle
    -0.46
    positorio
    -0.44
     pamamagitan
    -0.42
    brigens
    -0.41
     suporta
    -0.41
     couvert
    -0.41
     végétal
    -0.41
    ayy
    -0.40
    POSITIVE LOGITS
     age
    1.25
     Age
    1.19
     AGE
    1.16
    Age
    1.13
    age
    1.04
     ages
    0.95
    setAge
    0.88
    AGE
    0.86
     aged
    0.82
     Ages
    0.81
    Activations Density 0.068%

    No Known Activations