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. 262
    Prev
    Next
    INDEX
    Explanations

    email spam like content or unrelated text sequences

    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
    674
    +0.43
    1.8%
    764
    +0.40
    1.7%
    964
    +0.27
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.43
    0.04
    843
    +0.40
    0.01
    856
    +0.27
    0.03
    Negative Logits
     vry
    -0.64
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.62
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.61
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.58
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.58
     FFFF
    -0.57
     islamic
    -0.57
     Moslem
    -0.55
     iirc
    -0.54
     quelquefois
    -0.54
    POSITIVE LOGITS
    <bos>
    1.11
     nahilalakip
    0.63
     betweenstory
    0.60
    bewerken
    0.60
     дописавши
    0.57
     Vikipedi
    0.56
    商品説明
    0.55
     виправивши
    0.55
     gawas
    0.53
    SneakyThrows
    0.50
    Activations Density 0.188%

    No Known Activations