© 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. 14691
    Prev
    Next
    INDEX
    Explanations

    mentions of law enforcement activities and investigations

    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
    946
    +0.14
    0.4%
    658
    +0.12
    0.3%
    1499
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    658
    +0.14
    0.08
    1048
    +0.12
    0.04
    946
    +0.10
    0.06
    Negative Logits
     dirait
    -0.82
     trouva
    -0.81
     peppa
    -0.78
     tupperware
    -0.77
     ecru
    -0.77
     gouver
    -0.76
     gabri
    -0.74
     hairc
    -0.74
     giorgio
    -0.72
     cristina
    -0.72
    POSITIVE LOGITS
    Vaata
    0.59
    ("="
    0.57
    Referencoj
    0.56
     patrolling
    0.55
     investigating
    0.54
    Sqft
    0.54
     escort
    0.52
     patrol
    0.52
    Solución
    0.51
    Kaip
    0.51
    Activations Density 0.469%

    No Known Activations