© 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. 13340
    Prev
    Next
    INDEX
    Explanations

    phrases related to correcting errors or addressing 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
    +0.13
    0.4%
    604
    +0.12
    0.3%
    80
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.13
    0.05
    1322
    +0.12
    0.03
    1360
    +0.09
    0.03
    Negative Logits
     !...
    -0.87
     unden
    -0.86
    <bos>
    -0.85
     fluo
    -0.80
     fers
    -0.79
     attemp
    -0.79
     wherea
    -0.78
     compen
    -0.78
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.77
     honn
    -0.76
    POSITIVE LOGITS
     problems
    0.80
     problem
    0.74
     issues
    0.69
     shortcomings
    0.66
     deficiencies
    0.64
    problems
    0.63
     gaps
    0.62
     wrongs
    0.60
     imbalances
    0.60
     deficits
    0.60
    Activations Density 0.356%

    No Known Activations