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. 8227
    Prev
    Next
    INDEX
    Explanations

    descriptions of building projects and construction activities

    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
    599
    +0.10
    0.3%
    964
    +0.09
    0.3%
    694
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1336
    +0.10
    0.05
    694
    +0.09
    0.03
    599
    +0.08
    0.05
    Negative Logits
     BIBSYS
    -0.70
     automne
    -0.59
     outono
    -0.57
     CiNii
    -0.56
    propy
    -0.55
    Біографія
    -0.51
    Життєпис
    -0.51
     ++)
    -0.51
    ביוגרפיה
    -0.50
    aniline
    -0.49
    POSITIVE LOGITS
     evenings
    0.89
     afternoons
    0.87
     weekdays
    0.83
     daytime
    0.83
     nighttime
    0.83
     nocturnal
    0.81
     evening
    0.81
     weekday
    0.81
     mornings
    0.79
     midday
    0.78
    Activations Density 0.530%

    No Known Activations