© 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. 12753
    Prev
    Next
    INDEX
    Explanations

    instances of words and phrases related to personal relationships and actions

    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
    1741
    +0.13
    0.4%
    382
    +0.13
    0.4%
    1343
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.13
    0.08
    394
    +0.13
    0.06
    1806
    +0.13
    0.05
    Negative Logits
    ViewInit
    -0.79
    onAttach
    -0.68
     مشين
    -0.67
    TargetException
    -0.67
     meras
    -0.67
    Organisateur
    -0.66
    onOptions
    -0.66
    IGraphics
    -0.63
    !».
    -0.62
     mutu
    -0.61
    POSITIVE LOGITS
     ftu
    1.29
     fta
    1.17
     thut
    1.15
     perfon
    1.10
     fup
    1.07
     poff
    1.07
     fign
    1.06
     foon
    1.06
     intersper
    1.05
     ftre
    1.03
    Activations Density 0.423%

    No Known Activations