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. 15986
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'other' alongside specific nouns or adjectives

    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
    776
    +0.15
    0.5%
    897
    +0.12
    0.4%
    577
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1515
    +0.15
    0.03
    897
    +0.12
    0.03
    776
    +0.10
    0.04
    Negative Logits
    bufio
    -0.52
     TextFormField
    -0.50
    spania
    -0.48
    jména
    -0.47
     malattie
    -0.47
    })*/
    -0.46
     متعلقه
    -0.45
     tungkol
    -0.45
    saveButton
    -0.44
    σθαι
    -0.44
    POSITIVE LOGITS
    worldly
    0.79
     préfère
    0.69
     dirait
    0.65
     Autre
    0.64
     saurait
    0.59
     other
    0.56
     fasse
    0.56
    ngdoc
    0.53
     Aussi
    0.52
     pourrais
    0.52
    Activations Density 0.084%

    No Known Activations