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. 555
    Prev
    Next
    INDEX
    Explanations

    mentions of construction-related terms and activities

    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
    410
    +0.14
    0.5%
    411
    +0.11
    0.4%
    1065
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.14
    0.03
    411
    +0.11
    0.02
    1103
    +0.11
    0.02
    Negative Logits
    Și
    -0.68
    minipage
    -0.58
     superintend
    -0.57
     skimage
    -0.57
     prerog
    -0.54
     Whigs
    -0.54
     specialmente
    -0.53
     inol
    -0.51
     riusc
    -0.50
     alberto
    -0.49
    POSITIVE LOGITS
     construction
    1.22
     Construction
    1.18
    construction
    1.16
     CONSTRUCTION
    1.15
    Construction
    1.13
     constructions
    1.04
    CONSTRUCTION
    0.97
     construct
    0.96
     constructs
    0.95
    constructed
    0.91
    Activations Density 0.079%

    No Known Activations