© 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. 7451
    Prev
    Next
    INDEX
    Explanations

    phrases related to the decline in traditional industries and the rise of automation

    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
    520
    +0.07
    0.2%
    609
    +0.06
    0.2%
    1809
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1555
    +0.07
    0.03
    1718
    +0.06
    0.04
    1723
    +0.06
    0.03
    Negative Logits
     unspeak
    -1.01
     fortn
    -0.98
     shenan
    -0.92
     pamph
    -0.92
     depic
    -0.92
     apprehen
    -0.91
     reluct
    -0.88
     disagre
    -0.88
     volunte
    -0.88
     sophistic
    -0.87
    POSITIVE LOGITS
     original
    0.80
    original
    0.78
    Original
    0.75
     normalidad
    0.72
    ORIGINAL
    0.69
     originales
    0.68
    เดิม
    0.66
    normal
    0.65
     previous
    0.65
     normal
    0.65
    Activations Density 0.284%

    No Known Activations