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. 15255
    Prev
    Next
    INDEX
    Explanations

    dates expressed as four digits

    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
    1323
    +0.14
    0.5%
    577
    +0.14
    0.5%
    1363
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.14
    0.05
    577
    +0.14
    0.05
    1363
    +0.13
    0.04
    Negative Logits
    AlterField
    -0.47
     chi̍t
    -0.46
     ervoor
    -0.45
    klär
    -0.44
    bietet
    -0.44
    Wanneer
    -0.44
    Bardzo
    -0.43
    Élet
    -0.42
     exhortation
    -0.42
     Greens
    -0.42
    POSITIVE LOGITS
     abnorm
    0.88
     ohr
    0.85
     gero
    0.83
     elek
    0.83
     lapto
    0.82
     traktor
    0.82
     stik
    0.81
     lele
    0.79
     meis
    0.79
     kram
    0.77
    Activations Density 0.135%

    No Known Activations