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. 2283
    Prev
    Next
    INDEX
    Explanations

    dates and historical events, specifically focusing on the year 1966

    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
    1978
    +0.15
    0.4%
    776
    +0.13
    0.4%
    453
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.15
    0.09
    776
    +0.13
    0.07
    1295
    +0.10
    0.06
    Negative Logits
     tupperware
    -0.72
     automne
    -0.66
     oreo
    -0.65
     glycerin
    -0.61
     friable
    -0.60
     luxuriant
    -0.60
     feldspar
    -0.60
     scotch
    -0.59
     fusible
    -0.59
     taupe
    -0.58
    POSITIVE LOGITS
     silikon
    1.22
     makro
    1.14
     antik
    1.13
     akut
    1.12
     optik
    1.08
     alkoh
    1.07
     karton
    1.06
     mikrofon
    1.06
     kontinu
    1.06
     keramik
    1.03
    Activations Density 0.296%

    No Known Activations