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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13750
    Prev
    Next
    INDEX
    Explanations

    phrases related to political commentary

    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
    752
    +0.13
    0.4%
    190
    +0.09
    0.3%
    50
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.13
    0.05
    752
    +0.09
    0.04
    1207
    +0.09
    0.03
    Negative Logits
    <bos>
    -0.69
     Giugno
    -0.60
    rensa
    -0.51
     Luglio
    -0.51
     vostri
    -0.51
    mặt
    -0.48
     Conclu
    -0.47
    >\<
    -0.46
    ekyll
    -0.46
    Làm
    -0.46
    POSITIVE LOGITS
     fua
    0.55
     aen
    0.55
    hematical
    0.54
     lele
    0.53
     exportaciones
    0.51
    haviour
    0.50
     mme
    0.48
     tirage
    0.48
     vne
    0.48
    cnbc
    0.48
    Activations Density 0.223%

    No Known Activations