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. 15250
    Prev
    Next
    INDEX
    Explanations

    references to legal agreements and compliance with labor laws

    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
    1499
    +0.12
    0.4%
    1553
    +0.09
    0.3%
    1585
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.12
    0.09
    1585
    +0.09
    0.04
    1776
    +0.09
    0.03
    Negative Logits
     pixar
    -1.36
     indescri
    -1.29
     hairc
    -1.26
     jurassic
    -1.24
     impra
    -1.24
     milf
    -1.23
     inconce
    -1.22
     hentai
    -1.21
     snoopy
    -1.21
     Mlle
    -1.21
    POSITIVE LOGITS
     enforcement
    0.87
    enforcement
    0.75
     Enforcement
    0.71
     complaint
    0.63
     investigation
    0.63
     investigations
    0.62
    الدراسه
    0.61
     inspections
    0.60
     mergeFrom
    0.59
     enforce
    0.59
    Activations Density 0.614%

    No Known Activations