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. 8388
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparison or contrast

    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
    1334
    +0.12
    0.4%
    605
    +0.11
    0.4%
    889
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1805
    +0.12
    0.03
    356
    +0.11
    0.02
    938
    +0.11
    0.03
    Negative Logits
     trouva
    -0.53
     Violon
    -0.51
     Daarom
    -0.50
     Parametric
    -0.47
    Exponent
    -0.47
     Även
    -0.46
    DriverManager
    -0.46
    PLAUSE
    -0.45
    Bounded
    -0.45
     exemplaires
    -0.45
    POSITIVE LOGITS
     sento
    0.75
     aspetta
    0.74
     fortn
    0.65
     resorting
    0.62
     trovo
    0.62
     rendono
    0.62
     accla
    0.61
     encomp
    0.61
     volunte
    0.60
    kyou
    0.60
    Activations Density 0.077%

    No Known Activations