© 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. 7310
    Prev
    Next
    INDEX
    Explanations

    phrases related to accountability and project management issues

    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
    468
    +0.09
    0.3%
    1523
    +0.09
    0.2%
    581
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1005
    +0.09
    0.06
    1762
    +0.09
    0.04
    2044
    +0.07
    0.06
    Negative Logits
     „,
    -0.84
     pluri
    -0.84
     ?...
    -0.83
     meis
    -0.80
     ché
    -0.79
     purs
    -0.79
     incess
    -0.78
     uniqu
    -0.77
     solidar
    -0.77
     mef
    -0.77
    POSITIVE LOGITS
     caused
    0.73
     due
    0.70
     causing
    0.68
     resulting
    0.66
    URLException
    0.63
    due
    0.60
     leading
    0.56
     resulted
    0.55
    TargetException
    0.55
     causes
    0.54
    Activations Density 0.569%

    No Known Activations