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. 15494
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong emotions or opinions

    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
    1919
    +0.22
    0.7%
    1415
    +0.15
    0.5%
    825
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.22
    0.10
    1415
    +0.15
    0.07
    1265
    +0.11
    0.04
    Negative Logits
     Simult
    -1.15
     siena
    -1.10
     lele
    -1.08
     labd
    -1.07
     makro
    -1.07
     palab
    -1.07
     Keny
    -1.06
     Meksi
    -1.06
     alkoh
    -1.05
     parlamento
    -1.05
    POSITIVE LOGITS
    <bos>
    0.83
     want
    0.76
     have
    0.76
     ressemble
    0.71
     knew
    0.67
     survie
    0.67
     appreciate
    0.66
     cannot
    0.66
     beschik
    0.65
     think
    0.65
    Activations Density 0.282%

    No Known Activations