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. 13514
    Prev
    Next
    INDEX
    Explanations

    technical instructions and terms related to devices and technology

    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
    1842
    +0.15
    0.5%
    1819
    +0.13
    0.4%
    845
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1819
    +0.15
    0.10
    845
    +0.13
    0.06
    1870
    +0.12
    0.04
    Negative Logits
    AndEndTag
    -0.65
     kaynağından
    -0.64
    ftagPool
    -0.60
    клопе
    -0.59
    aarrggbb
    -0.57
     שוליים
    -0.56
     surla
    -0.56
    Espèce
    -0.55
     Савезне
    -0.54
    Према
    -0.54
    POSITIVE LOGITS
     disagre
    1.52
     encomp
    1.46
     inev
    1.43
     shenan
    1.42
     increa
    1.38
     reluct
    1.38
     uninten
    1.36
     accla
    1.35
     depic
    1.33
     excru
    1.32
    Activations Density 0.915%

    No Known Activations