© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7221
    Prev
    Next
    INDEX
    Explanations

    terms related to aviation accidents, such as "crash", "survivability", and "Federal Aviation Administration"

    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
    680
    +0.13
    0.5%
    421
    +0.13
    0.5%
    896
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    680
    +0.13
    0.02
    203
    +0.13
    0.02
    421
    +0.12
    0.02
    Negative Logits
    ceptives
    -0.59
    🕗
    -0.49
    OGND
    -0.49
     interessa
    -0.49
    giv
    -0.46
    სქოლიო
    -0.45
     vedo
    -0.45
    '},
    
    -0.44
     Wicidata
    -0.44
     pú
    -0.43
    POSITIVE LOGITS
     crash
    1.38
     Crash
    1.31
    crash
    1.29
    Crash
    1.23
     crashes
    1.18
     crashing
    1.11
     crashed
    1.08
     Cras
    1.04
     Shakspeare
    0.82
    cras
    0.82
    Activations Density 0.071%

    No Known Activations