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. 363
    Prev
    Next
    INDEX
    Explanations

    words related to research experiments and data analysis, such as "experiments," "participants," and "rate."

    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
    876
    +0.10
    0.3%
    674
    +0.10
    0.3%
    1385
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1836
    +0.10
    0.01
    718
    +0.10
    0.02
    407
    +0.10
    0.02
    Negative Logits
     pamph
    -0.62
     nôtre
    -0.59
     obstin
    -0.57
     suivie
    -0.54
     Adjutant
    -0.54
     poetical
    -0.54
     Hauptmann
    -0.53
     Shakspeare
    -0.53
    ContentAsync
    -0.52
    Gweler
    -0.51
    POSITIVE LOGITS
    <bos>
    1.08
    thinkable
    0.53
    wavering
    0.50
    sightly
    0.50
    ⓧ
    0.46
     mondeo
    0.45
    nemia
    0.45
     depres
    0.44
    relenting
    0.43
     duster
    0.43
    Activations Density 0.175%

    No Known Activations