© 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. 12939
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic impact or societal 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
    752
    +0.15
    0.5%
    1042
    +0.14
    0.5%
    453
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.15
    0.07
    16
    +0.14
    0.07
    1156
    +0.14
    0.04
    Negative Logits
    ⓧ
    -0.68
     provoque
    -0.65
     contribue
    -0.62
     assiste
    -0.62
    
    -0.61
     lapto
    -0.60
    <?
    -0.60
    VYMaps
    -0.59
     exé
    -0.59
     gagne
    -0.59
    POSITIVE LOGITS
     stratigraph
    0.91
     Grecian
    0.88
     lovel
    0.84
     countryman
    0.81
     inext
    0.81
     underta
    0.81
     Longfellow
    0.79
     cuck
    0.79
     Daven
    0.79
     vagu
    0.78
    Activations Density 0.422%

    No Known Activations