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. 15467
    Prev
    Next
    INDEX
    Explanations

    references to technology and technical terms

    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
    1577
    +0.20
    0.7%
    50
    +0.18
    0.7%
    964
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1654
    +0.20
    0.15
    227
    +0.18
    0.21
    1987
    +0.14
    0.09
    Negative Logits
    település
    -0.90
    ⓧ
    -0.79
     autorytatywna
    -0.79
     CiNii
    -0.78
    astéro
    -0.76
    municipi
    -0.74
    kháu
    -0.73
    tonode
    -0.72
    WriteBarrier
    -0.71
    SneakyThrows
    -0.70
    POSITIVE LOGITS
     maneu
    0.74
     inappro
    0.69
     attemp
    0.69
    uxx
    0.69
     impra
    0.68
     ineffec
    0.66
     inev
    0.66
     shenan
    0.64
     egreg
    0.64
     Sarm
    0.62
    Activations Density 5.154%

    No Known Activations