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. 1415
    Prev
    Next
    INDEX
    Explanations

    phrases related to simplicity and plans

    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
    680
    +0.13
    0.5%
    1363
    +0.13
    0.5%
    1964
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    680
    +0.13
    0.03
    1793
    +0.13
    0.03
    1964
    +0.13
    0.03
    Negative Logits
     depic
    -1.04
     intersper
    -1.00
     shenan
    -0.99
     disagre
    -0.97
     inappro
    -0.95
     gild
    -0.93
     accla
    -0.92
     encomp
    -0.92
     apprehen
    -0.90
     Shakspeare
    -0.89
    POSITIVE LOGITS
     simple
    1.17
    simple
    1.12
    Simple
    1.12
     Simple
    1.10
     simples
    1.02
    SIMPLE
    0.98
     SIMPLE
    0.93
     simplest
    0.84
     simplicity
    0.82
     simpler
    0.82
    Activations Density 0.076%

    No Known Activations