© 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. 6781
    Prev
    Next
    INDEX
    Explanations

    phrases related to humanitarian crises and lack of basic necessities

    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
    549
    +0.08
    0.2%
    1216
    +0.08
    0.2%
    1253
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1216
    +0.08
    0.04
    392
    +0.08
    0.02
    2045
    +0.08
    0.04
    Negative Logits
     vernac
    -0.62
     plis
    -0.62
     suspic
    -0.62
     emble
    -0.60
     dissi
    -0.60
     qed
    -0.60
     diagon
    -0.60
     compil
    -0.60
     Bén
    -0.59
     Præ
    -0.59
    POSITIVE LOGITS
     access
    0.66
     resources
    0.63
     adequate
    0.62
     decent
    0.58
     opportunities
    0.55
     amenities
    0.55
     proper
    0.54
     affordable
    0.52
    resources
    0.51
    access
    0.50
    Activations Density 0.383%

    No Known Activations