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. 8402
    Prev
    Next
    INDEX
    Explanations

    references to specific provinces, locations, and events

    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
    227
    +0.10
    0.3%
    1499
    +0.10
    0.3%
    395
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.10
    0.06
    395
    +0.10
    0.04
    20
    +0.09
    0.04
    Negative Logits
     chong
    -1.29
     kyo
    -1.28
     guarante
    -1.26
     XIA
    -1.26
     bangkok
    -1.26
     increa
    -1.20
     chrysler
    -1.20
     seoul
    -1.19
     chande
    -1.19
     eyel
    -1.18
    POSITIVE LOGITS
    antd
    0.82
    Bei
    0.68
    mybatisplus
    0.65
     China
    0.65
     Bei
    0.64
     Chinese
    0.63
    Dazu
    0.62
    China
    0.62
    Xinhua
    0.61
    Chinese
    0.60
    Activations Density 0.254%

    No Known Activations