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. 10-RES-JB
    6. 1191
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "out" and its variations, as well as expressions of expenditure or effort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.24
    0.9%
    1253
    +0.12
    0.4%
    1387
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1253
    +0.24
    0.03
    897
    +0.12
    0.04
    1387
    +0.11
    0.04
    Negative Logits
    <bos>
    -1.92
    app
    -0.64
     spoke
    -0.63
     told
    -0.60
    for
    -0.60
     propose
    -0.59
     brought
    -0.59
     began
    -0.59
     said
    -0.58
    //---
    -0.58
    POSITIVE LOGITS
     considér
    1.40
     Juf
    1.40
     swarovski
    1.34
     saar
    1.31
     maksi
    1.31
     ecru
    1.31
     jaya
    1.31
     rafra
    1.30
     palio
    1.30
     bandung
    1.28
    Activations Density 0.311%

    No Known Activations