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. 15719
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or requirements

    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
    1919
    +0.11
    0.3%
    783
    +0.10
    0.3%
    674
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.11
    0.04
    1919
    +0.10
    0.05
    411
    +0.10
    0.04
    Negative Logits
     palio
    -0.77
     Bibl
    -0.75
     masaj
    -0.74
     Chinois
    -0.73
    idance
    -0.72
     LXX
    -0.72
     Quod
    -0.72
     Britann
    -0.71
     Mémoires
    -0.71
     Græ
    -0.69
    POSITIVE LOGITS
     notice
    0.65
     noticed
    0.61
     youll
    0.61
     find
    0.60
     need
    0.60
    GEBURTSDATUM
    0.58
     receive
    0.57
     see
    0.56
     recieve
    0.55
     noticing
    0.54
    Activations Density 0.164%

    No Known Activations