© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12263
    Prev
    Next
    INDEX
    Explanations

    statistical and economic terms and concepts

    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
    297
    +0.12
    0.4%
    876
    +0.10
    0.3%
    1699
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.12
    0.07
    51
    +0.10
    0.03
    297
    +0.10
    0.06
    Negative Logits
    Referencie
    -0.70
    aarrggbb
    -0.69
    Zdroje
    -0.67
    Geplaatst
    -0.66
    Jegyzetek
    -0.63
    ganu
    -0.63
    CROSSTALK
    -0.63
    ContentAsync
    -0.62
    Dimensiones
    -0.61
    bcryptjs
    -0.61
    POSITIVE LOGITS
     reluct
    1.79
     increa
    1.73
     maneu
    1.73
     impra
    1.69
     disagre
    1.65
     guarante
    1.65
     erad
    1.63
     strick
    1.61
     inev
    1.60
     affor
    1.59
    Activations Density 0.650%

    No Known Activations