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. 606
    Prev
    Next
    INDEX
    Explanations

    descriptions of technical features and components of a vehicle

    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
    1150
    +0.17
    0.5%
    1438
    +0.17
    0.5%
    332
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1819
    +0.17
    0.08
    1438
    +0.17
    0.05
    332
    +0.12
    0.06
    Negative Logits
     ftu
    -1.52
     fuf
    -1.46
     Abbé
    -1.44
     Souha
    -1.43
     Mlle
    -1.43
     emphat
    -1.43
     squa
    -1.42
     reluct
    -1.42
     disagre
    -1.41
     perfet
    -1.41
    POSITIVE LOGITS
    .
    0.91
    ().
    0.78
     etc
    0.77
    。
    0.73
    ."
    0.69
    etc
    0.68
    ).
    0.68
    ].
    0.68
     ।
    0.67
    .”
    0.67
    Activations Density 0.626%

    No Known Activations