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. 1435
    Prev
    Next
    INDEX
    Explanations

    mentions of hiring difficulties and personnel processes in a workplace setting

    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
    1661
    +0.09
    0.2%
    1553
    +0.08
    0.2%
    792
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.09
    0.06
    392
    +0.08
    0.02
    1038
    +0.07
    0.03
    Negative Logits
     cytoplas
    -0.87
     macrop
    -0.86
     malheur
    -0.86
     vœ
    -0.76
     marchand
    -0.76
     uncin
    -0.75
     tranf
    -0.73
     poichè
    -0.73
     poff
    -0.73
     monstre
    -0.73
    POSITIVE LOGITS
     recruitment
    1.04
     recruiting
    1.00
     Recruitment
    0.90
     recruit
    0.90
     hiring
    0.87
     recruits
    0.84
    Recruitment
    0.82
     recruited
    0.79
     applicants
    0.78
     Recruiting
    0.77
    Activations Density 0.720%

    No Known Activations