© 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. 13673
    Prev
    Next
    INDEX
    Explanations

    news articles about crimes and police activities

    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
    2019
    +0.17
    0.5%
    924
    +0.11
    0.3%
    1133
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1133
    +0.17
    0.04
    1515
    +0.11
    0.03
    1921
    +0.10
    0.04
    Negative Logits
     velour
    -0.65
     recessive
    -0.55
     schoolmaster
    -0.54
     Cárdenas
    -0.54
     startX
    -0.53
     wanderer
    -0.51
     portico
    -0.51
     dachshund
    -0.51
    Jakie
    -0.51
    церт
    -0.50
    POSITIVE LOGITS
     ordina
    0.99
     vitale
    0.96
     fatis
    0.92
     utop
    0.90
     dispen
    0.86
     incess
    0.86
     socie
    0.85
     elek
    0.85
     minimalis
    0.85
     estimat
    0.84
    Activations Density 0.075%

    No Known Activations