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. 8420
    Prev
    Next
    INDEX
    Explanations

    phrases related to travel and technology

    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
    658
    +0.17
    0.5%
    381
    +0.11
    0.3%
    478
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    658
    +0.17
    0.07
    1919
    +0.11
    0.04
    47
    +0.11
    0.04
    Negative Logits
     provoque
    -0.84
     viendra
    -0.73
     moza
    -0.72
     hej
    -0.69
     balon
    -0.68
     kac
    -0.67
     kask
    -0.67
     remonte
    -0.66
     utop
    -0.66
     karton
    -0.65
    POSITIVE LOGITS
     xxii
    0.67
     xxv
    0.67
     interested
    0.67
     ryzen
    0.66
     unsure
    0.66
     xxvi
    0.66
    Jeśli
    0.64
     able
    0.64
     Eğer
    0.64
    LEGGI
    0.63
    Activations Density 0.152%

    No Known Activations