© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3976
    Prev
    Next
    INDEX
    Explanations

    phrases related to efforts or attempts

    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
    32
    +0.11
    0.3%
    674
    +0.10
    0.3%
    1527
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    971
    +0.11
    0.02
    1162
    +0.10
    0.02
    1450
    +0.10
    0.01
    Negative Logits
     reluct
    -1.55
     embra
    -1.53
     accla
    -1.43
     inconce
    -1.41
     mef
    -1.41
     indestru
    -1.40
     fuf
    -1.40
     madonna
    -1.40
     increa
    -1.40
     disagre
    -1.39
    POSITIVE LOGITS
    <bos>
    0.92
    djangoproject
    0.66
     least
    0.63
     betweenstory
    0.63
     الحره
    0.60
    至少
    0.58
    jmniej
    0.57
     minimum
    0.56
     decent
    0.55
    HomeAsUpEnabled
    0.55
    Activations Density 0.074%

    No Known Activations