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. 8177
    Prev
    Next
    INDEX
    Explanations

    words related to construction and physical labor activities

    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
    1407
    +0.19
    1.1%
    390
    +0.17
    0.9%
    920
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1577
    +0.19
    0.04
    390
    +0.17
    0.03
    920
    +0.15
    0.03
    Negative Logits
    <bos>
    -1.28
    contentLoaded
    -0.67
    Brainz
    -0.66
    jsxFileName
    -0.64
     Kle
    -0.64
     linkovi
    -0.62
    انجليز
    -0.62
    хьтан
    -0.62
    object
    -0.59
    Object
    -0.58
    POSITIVE LOGITS
     disreg
    1.18
     hairc
    1.12
     soggior
    1.12
     swarovski
    1.11
     ecru
    1.09
     indestru
    1.09
     maroc
    1.08
     pymysql
    1.07
     ricardo
    1.06
     thermomix
    1.02
    Activations Density 0.442%

    No Known Activations