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. 1409
    Prev
    Next
    INDEX
    Explanations

    phrases related to polyamory and relationship dynamics

    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
    1622
    +0.17
    0.7%
    1520
    +0.12
    0.5%
    1387
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1622
    +0.17
    0.02
    689
    +0.12
    0.02
    120
    +0.12
    0.02
    Negative Logits
     Kriege
    -0.46
    TargetException
    -0.44
    BRACKET
    -0.43
    carboxylic
    -0.42
     Erbe
    -0.42
    meiras
    -0.42
    乓
    -0.42
     سكانية
    -0.42
     Dingen
    -0.41
     ביותר
    -0.41
    POSITIVE LOGITS
     poly
    1.40
    Poly
    1.39
    poly
    1.36
     Poly
    1.35
     POLY
    1.15
    POLY
    1.13
     polyg
    1.05
     poli
    0.87
     polig
    0.86
     polyps
    0.82
    Activations Density 0.082%

    No Known Activations