© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13073
    Prev
    Next
    INDEX
    Explanations

    phrases related to political talks and actions

    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
    1799
    +0.07
    0.2%
    208
    +0.07
    0.2%
    307
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    916
    +0.07
    0.03
    1799
    +0.07
    0.01
    1014
    +0.07
    0.03
    Negative Logits
     reluct
    -1.47
     increa
    -1.46
     suspic
    -1.46
     inev
    -1.45
     desir
    -1.41
     maneu
    -1.41
     accla
    -1.41
     disagre
    -1.41
     disgra
    -1.40
     depic
    -1.40
    POSITIVE LOGITS
     actions
    0.94
    actions
    0.89
     actual
    0.89
    Actions
    0.87
    actual
    0.86
     action
    0.84
    action
    0.81
    Actual
    0.77
     actually
    0.75
     Actions
    0.75
    Activations Density 0.441%

    No Known Activations