© 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. 13734
    Prev
    Next
    INDEX
    Explanations

    mentions of tax cuts and related financial terms within a political context

    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
    994
    +0.10
    0.3%
    1385
    +0.08
    0.2%
    549
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.10
    0.04
    919
    +0.08
    0.02
    1948
    +0.08
    0.04
    Negative Logits
     secon
    -1.74
     increa
    -1.69
     desir
    -1.64
     volunte
    -1.62
     embra
    -1.62
     emphat
    -1.62
     effe
    -1.61
     guarante
    -1.61
     perfet
    -1.60
     inev
    -1.60
    POSITIVE LOGITS
     for
    0.69
     für
    0.61
     для
    0.61
     voor
    0.60
     tax
    0.60
     offered
    0.60
     granted
    0.58
     announced
    0.57
     dla
    0.57
     from
    0.56
    Activations Density 0.192%

    No Known Activations