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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 9027
    Prev
    Next
    INDEX
    Explanations

    phrases related to ancient civilizations and cultural heritage

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.21
    0.9%
    1967
    +0.10
    0.4%
    478
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1987
    +0.21
    0.13
    690
    +0.10
    0.11
    86
    +0.10
    0.08
    Negative Logits
    <bos>
    -3.58
    Autoritní
    -1.13
     Roskov
    -1.08
    ⓧ
    -1.06
     autorytatywna
    -1.01
     Мексичка
    -1.00
     bezeichneter
    -0.91
    StoreMessageInfo
    -0.90
    Билгалдахарш
    -0.89
    Vidite
    -0.89
    POSITIVE LOGITS
     increa
    1.65
     stockholm
    1.65
     wien
    1.62
     inev
    1.61
     ?...
    1.56
     fto
    1.54
     fuf
    1.54
     unden
    1.54
     oner
    1.53
     erad
    1.53
    Activations Density 1.119%

    No Known Activations