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. 15788
    Prev
    Next
    INDEX
    Explanations

    social media links

    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
    1343
    +0.18
    0.5%
    924
    +0.10
    0.3%
    1145
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1062
    +0.18
    0.02
    981
    +0.10
    0.02
    924
    +0.09
    0.02
    Negative Logits
     shewn
    -0.69
     Ribera
    -0.65
     barbarous
    -0.61
     Michoacán
    -0.60
     implacable
    -0.59
     withal
    -0.59
     despotism
    -0.58
     gaily
    -0.58
     warlike
    -0.56
     idolat
    -0.56
    POSITIVE LOGITS
     romantique
    0.77
     confé
    0.76
     héro
    0.72
     charmant
    0.69
     joyeux
    0.69
     authentique
    0.68
     recueil
    0.68
     asiatique
    0.67
     incroy
    0.66
     coloré
    0.65
    Activations Density 0.037%

    No Known Activations