© 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. 4043
    Prev
    Next
    INDEX
    Explanations

    references to historical events, particularly the Kennedy assassination

    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
    204
    +0.18
    0.7%
    1671
    +0.14
    0.6%
    893
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.18
    0.02
    395
    +0.14
    0.03
    950
    +0.12
    0.03
    Negative Logits
    OGND
    -0.54
     հղումներ
    -0.51
    MLLoader
    -0.50
    autoIncrement
    -0.50
     nakalista
    -0.50
    userdetails
    -0.49
     sierp
    -0.48
    Vielleicht
    -0.47
    RTEE
    -0.47
    脚注の使い方
    -0.46
    POSITIVE LOGITS
     Kennedy
    1.54
    Kennedy
    1.37
     JFK
    1.13
     KENN
    0.95
     kenn
    0.92
    JFK
    0.90
     Kenn
    0.82
     Lég
    0.66
     Sén
    0.64
     rouleau
    0.63
    Activations Density 0.128%

    No Known Activations