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. 1770
    Prev
    Next
    INDEX
    Explanations

    text related to historical or political events and entities

    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
    50
    +0.27
    1.2%
    1967
    +0.24
    1.0%
    394
    +0.23
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.27
    0.17
    1967
    +0.24
    0.13
    50
    +0.23
    0.30
    Negative Logits
    <bos>
    -1.40
     виправивши
    -0.91
     Campionato
    -0.85
     FBref
    -0.84
     soggior
    -0.84
    Personensuche
    -0.83
    bewerken
    -0.83
     himo
    -0.83
     abbra
    -0.80
    RegressionTest
    -0.80
    POSITIVE LOGITS
     reluct
    0.96
     unspeak
    0.95
     shenan
    0.93
     ineffec
    0.92
     apprehen
    0.92
     disagre
    0.91
     sophistic
    0.91
     McLaugh
    0.90
     philanth
    0.88
     Bengt
    0.86
    Activations Density 12.944%

    No Known Activations