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. 13579
    Prev
    Next
    INDEX
    Explanations

    names of categories or labels within a system

    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
    1343
    +0.13
    0.4%
    453
    +0.12
    0.3%
    1978
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.13
    0.02
    1108
    +0.12
    0.02
    453
    +0.11
    0.02
    Negative Logits
     jsPsych
    -0.70
     mergeFrom
    -0.70
    contentLoaded
    -0.67
    JspWriter
    -0.65
     betweenstory
    -0.64
    complexContent
    -0.63
    ցված
    -0.63
    Bibliograf
    -0.61
     '{@
    -0.60
    ;%%
    -0.60
    POSITIVE LOGITS
     squa
    1.70
     unden
    1.69
     strick
    1.67
     inev
    1.66
     stockholm
    1.65
     ?...
    1.64
     increa
    1.63
     volunte
    1.61
     affor
    1.61
     compen
    1.61
    Activations Density 0.032%

    No Known Activations