Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15895
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical wiring and instructions for handling electrical equipment

    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
    272
    +0.07
    0.2%
    1839
    +0.07
    0.2%
    974
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.07
    0.07
    974
    +0.07
    0.04
    1649
    +0.07
    0.05
    Negative Logits
     fte
    -1.22
     effe
    -1.18
     fuf
    -1.17
     ?...
    -1.17
     ivi
    -1.17
     sii
    -1.16
     secon
    -1.15
     oner
    -1.15
     guarante
    -1.15
     encomp
    -1.13
    POSITIVE LOGITS
     necessary
    0.91
     needed
    0.84
    necessary
    0.77
     required
    0.76
    needed
    0.68
     الرياضيه
    0.67
    HideFlags
    0.67
     mentioned
    0.66
     requested
    0.66
     disambiguazione
    0.62
    Activations Density 0.644%

    No Known Activations