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. 8345
    Prev
    Next
    INDEX
    Explanations

    phrases related to network addressing and communication

    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
    876
    +0.17
    0.5%
    509
    +0.11
    0.3%
    1533
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.17
    -0.01
    1446
    +0.11
    0.02
    505
    +0.11
    0.01
    Negative Logits
    cmos
    -0.45
     bakteri
    -0.45
    toxins
    -0.45
     Demokrat
    -0.45
    vcpu
    -0.43
    IsContent
    -0.43
     konserv
    -0.42
     solemnity
    -0.41
    smp
    -0.41
     Bakar
    -0.41
    POSITIVE LOGITS
     nutella
    1.00
     thermomix
    0.99
     bonjour
    0.96
     tupperware
    0.95
     oleo
    0.94
     milano
    0.89
     peugeot
    0.89
     lidl
    0.89
     lamborghini
    0.88
     vespa
    0.87
    Activations Density 0.307%

    No Known Activations