© 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. 13399
    Prev
    Next
    INDEX
    Explanations

    phrases related to blame and responsibility

    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
    674
    +0.10
    0.3%
    468
    +0.08
    0.2%
    62
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.10
    0.04
    744
    +0.08
    0.03
    847
    +0.08
    0.02
    Negative Logits
     uninten
    -0.82
     dilap
    -0.82
     seclu
    -0.80
     impra
    -0.79
     reluct
    -0.76
     resear
    -0.76
     unve
    -0.75
     Kün
    -0.72
     depic
    -0.72
     saar
    -0.72
    POSITIVE LOGITS
    ciless
    0.65
    SharedDtor
    0.50
    mbad
    0.50
    pexpr
    0.50
     blame
    0.49
     AssertionError
    0.49
    eload
    0.48
    ündigt
    0.48
    utriche
    0.48
     somehow
    0.47
    Activations Density 0.329%

    No Known Activations