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. 13547
    Prev
    Next
    INDEX
    Explanations

    text indicating the importance of something

    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
    168
    +0.13
    0.4%
    196
    +0.12
    0.4%
    1527
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.13
    0.05
    1372
    +0.12
    0.05
    240
    +0.11
    0.04
    Negative Logits
     tenté
    -0.67
     excès
    -0.65
     oeil
    -0.63
     écart
    -0.59
     rendono
    -0.58
     saad
    -0.58
     endeavouring
    -0.58
     alip
    -0.57
     suna
    -0.56
     maksi
    -0.56
    POSITIVE LOGITS
     important
    0.84
     importance
    0.83
     Important
    0.81
    important
    0.79
    Important
    0.71
     Importance
    0.70
    importance
    0.70
     importants
    0.68
    Importance
    0.66
     IMPORTANT
    0.65
    Activations Density 0.140%

    No Known Activations