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. 16049
    Prev
    Next
    INDEX
    Explanations

    lyrical phrases or verses related to taunting, fighting, or challenging others

    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
    325
    +0.11
    0.3%
    674
    +0.10
    0.3%
    577
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1558
    +0.11
    0.06
    1343
    +0.10
    0.05
    382
    +0.10
    0.05
    Negative Logits
     impra
    -0.96
     intersper
    -0.93
     horrend
    -0.89
     increa
    -0.87
     unspeak
    -0.87
     ineffec
    -0.85
     indescri
    -0.84
     perchance
    -0.83
     attemp
    -0.83
     vainly
    -0.83
    POSITIVE LOGITS
     hunde
    0.83
     alkoh
    0.76
     nena
    0.71
    PerformLayout
    0.70
     habet
    0.70
     solidar
    0.69
     silang
    0.67
     rente
    0.67
     kompati
    0.66
     meras
    0.66
    Activations Density 0.182%

    No Known Activations