© 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 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. 10971
    Prev
    Next
    INDEX
    Explanations

    phrases related to membership in an organization

    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
    597
    +0.12
    0.4%
    1870
    +0.12
    0.4%
    757
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1778
    +0.12
    0.03
    544
    +0.12
    0.04
    130
    +0.11
    0.04
    Negative Logits
     pessi
    -0.95
     fluo
    -0.91
     effe
    -0.90
     robus
    -0.89
     socie
    -0.88
     circonst
    -0.86
     emble
    -0.86
     trit
    -0.86
     délib
    -0.84
     autorité
    -0.81
    POSITIVE LOGITS
    orship
    0.86
     membership
    0.82
     presidency
    0.67
     partnership
    0.64
     skjø
    0.63
     Membership
    0.63
    ership
    0.62
     ownership
    0.61
     tenure
    0.59
     sponsorship
    0.59
    Activations Density 0.205%

    No Known Activations