© 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 EvalsExportsinterp-engineNEWAPI 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. 15210
    Prev
    Next
    INDEX
    Explanations

    software-related terms

    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
    1870
    +0.17
    0.7%
    1581
    +0.15
    0.6%
    1705
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1581
    +0.17
    0.02
    1705
    +0.15
    0.03
    489
    +0.12
    0.02
    Negative Logits
     accla
    -0.67
     idolat
    -0.67
     racon
    -0.63
     milf
    -0.62
     nicolas
    -0.59
     fash
    -0.59
     hugo
    -0.59
     disgra
    -0.58
     fann
    -0.57
     pamph
    -0.57
    POSITIVE LOGITS
     software
    1.37
     Software
    1.22
    Software
    1.22
    software
    1.21
     SOFTWARE
    1.11
    SOFTWARE
    0.96
    软件
    0.95
     softwares
    0.82
    oftware
    0.77
     logiciel
    0.72
    Activations Density 0.064%

    No Known Activations