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. 15960
    Prev
    Next
    INDEX
    Explanations

    phrases related to construction and development projects

    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
    1120
    +0.15
    0.4%
    939
    +0.14
    0.4%
    1499
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.15
    0.08
    1499
    +0.14
    0.06
    392
    +0.10
    0.03
    Negative Logits
     smtplib
    -0.86
     milf
    -0.80
     luffy
    -0.79
    YMMV
    -0.79
     pymysql
    -0.78
     cytoplas
    -0.78
     yoda
    -0.75
     Wtf
    -0.75
     inconce
    -0.74
     Lmao
    -0.74
    POSITIVE LOGITS
     proposed
    0.59
    proposed
    0.54
    styleType
    0.54
    Geografi
    0.54
     سكانية
    0.53
     zoning
    0.53
     approval
    0.51
     site
    0.50
    pushFollow
    0.50
    UnusedPrivate
    0.49
    Activations Density 0.513%

    No Known Activations