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. 2985
    Prev
    Next
    INDEX
    Explanations

    mentions about banking-related complaints and resolutions

    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
    946
    +0.11
    0.3%
    1553
    +0.09
    0.3%
    2016
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.11
    0.05
    1553
    +0.09
    0.05
    946
    +0.09
    0.04
    Negative Logits
    printList
    -0.56
    Hombre
    -0.54
    Alors
    -0.53
    Loading
    -0.52
    Mientras
    -0.50
    textEdit
    -0.48
    Charsets
    -0.48
     dezembro
    -0.48
    PasswordField
    -0.48
    onPause
    -0.48
    POSITIVE LOGITS
     gild
    0.84
     cushi
    0.83
     affor
    0.81
     inappro
    0.79
     panama
    0.79
     embodi
    0.79
     Ename
    0.76
     suscep
    0.76
     snoopy
    0.76
     squa
    0.76
    Activations Density 0.417%

    No Known Activations