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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16273
    Prev
    Next
    INDEX
    Explanations

    mentions of migrants and migration-related terms

    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
    1482
    +0.14
    0.6%
    1325
    +0.13
    0.5%
    410
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1407
    +0.14
    0.02
    410
    +0.13
    0.02
    544
    +0.12
    0.02
    Negative Logits
     AssemblyCompany
    -0.56
     Compañ
    -0.53
     Ropa
    -0.51
    indro
    -0.49
    uxxxx
    -0.48
    OGND
    -0.47
     Explora
    -0.46
     PEDRO
    -0.46
     PAZ
    -0.45
     Timoteo
    -0.45
    POSITIVE LOGITS
     Mig
    1.40
    Mig
    1.34
     migration
    1.29
     migrants
    1.23
     Migration
    1.17
    migration
    1.13
     mig
    1.13
    mig
    1.12
     migrant
    1.12
     migrations
    1.09
    Activations Density 0.048%

    No Known Activations