© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12847
    Prev
    Next
    INDEX
    Explanations

    detail about personal experiences and family dynamics, particularly related to rebellion against cultural expectations

    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
    394
    +0.39
    1.5%
    1577
    +0.30
    1.2%
    50
    +0.19
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.39
    0.18
    184
    +0.30
    0.05
    16
    +0.19
    0.17
    Negative Logits
    <bos>
    -0.57
    íí
    -0.52
     Biôgrafia
    -0.51
    ECONDS
    -0.51
    Geplaatst
    -0.48
    .
    -0.47
     PeEnEo
    -0.44
    AndroidJUnit
    -0.44
    رشف
    -0.44
     gawas
    -0.44
    POSITIVE LOGITS
     ftu
    1.00
     ftre
    0.97
     aen
    0.95
     fua
    0.94
     fup
    0.89
     fta
    0.88
     waer
    0.87
    «<
    0.85
     vns
    0.84
     fign
    0.83
    Activations Density 4.683%

    No Known Activations