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. 8430
    Prev
    Next
    INDEX
    Explanations

    organizations or groups of people

    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
    227
    +0.23
    0.7%
    2006
    +0.12
    0.4%
    1177
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.23
    0.10
    74
    +0.12
    0.05
    1252
    +0.12
    0.05
    Negative Logits
    <bos>
    -1.01
     Paglinawan
    -0.68
    sonance
    -0.63
    BeforeMethod
    -0.60
     propOrder
    -0.60
    sendRedirect
    -0.57
    towania
    -0.55
    irability
    -0.55
     '\\;'
    -0.54
     kasarigan
    -0.54
    POSITIVE LOGITS
     Juf
    1.59
     Bartholo
    1.55
     Gorb
    1.54
     Rine
    1.44
     Sted
    1.39
     Kün
    1.37
     McLaugh
    1.37
     Abbé
    1.34
     Mlle
    1.34
     depic
    1.32
    Activations Density 0.682%

    No Known Activations