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. 738
    Prev
    Next
    INDEX
    Explanations

    phrases related to sharing information, thoughts, or stories

    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
    1187
    +0.13
    0.4%
    1618
    +0.12
    0.4%
    131
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1187
    +0.13
    0.03
    1437
    +0.12
    0.04
    131
    +0.11
    0.03
    Negative Logits
    bindParam
    -0.51
    Condol
    -0.51
    ⓧ
    -0.50
    /**
    -0.50
    ApiController
    -0.48
    marginHorizontal
    -0.47
    原始内容
    -0.47
    getLastName
    -0.47
    paddingVertical
    -0.47
     traduce
    -0.47
    POSITIVE LOGITS
    share
    1.14
     share
    1.14
     Share
    1.12
     Sharing
    1.11
     sharing
    1.10
     SHARE
    1.08
    sharing
    1.07
    Share
    1.06
     shares
    1.04
    Sharing
    1.02
    Activations Density 0.075%

    No Known Activations