© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13827
    Prev
    Next
    INDEX
    Explanations

    words related to emotions and reactions, especially negative emotions like disgust, anger, and upset

    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
    1056
    +0.12
    0.3%
    1013
    +0.12
    0.3%
    1141
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1056
    +0.12
    0.07
    247
    +0.12
    0.06
    1490
    +0.09
    0.06
    Negative Logits
     meras
    -0.88
     utop
    -0.85
     makro
    -0.83
     kram
    -0.77
     elek
    -0.77
     hunde
    -0.71
     paus
    -0.71
     ortop
    -0.70
     sement
    -0.70
     palet
    -0.70
    POSITIVE LOGITS
     Plotting
    0.64
     about
    0.62
     by
    0.53
     INPUTS
    0.53
     Iterate
    0.51
    jątk
    0.51
     Initialise
    0.49
    ness
    0.49
     because
    0.48
     Parsing
    0.47
    Activations Density 0.228%

    No Known Activations