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. 15109
    Prev
    Next
    INDEX
    Explanations

    instructions on applying themes or downloading applications

    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
    453
    +0.15
    0.4%
    1150
    +0.08
    0.2%
    766
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.15
    0.04
    678
    +0.08
    0.04
    1415
    +0.08
    0.02
    Negative Logits
     Valentín
    -0.86
     Áng
    -0.85
     Darío
    -0.82
     Abbé
    -0.79
     Marín
    -0.76
     Sinal
    -0.75
     ivi
    -0.74
     Almería
    -0.74
     Coim
    -0.73
     Cádiz
    -0.73
    POSITIVE LOGITS
    simply
    0.68
    einf
    0.65
     simply
    0.63
    Simply
    0.59
     Simply
    0.59
     entweder
    0.57
     zupeł
    0.56
    Einfach
    0.56
    <bos>
    0.56
    niosek
    0.54
    Activations Density 0.256%

    No Known Activations