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. 13505
    Prev
    Next
    INDEX
    Explanations

    dialogue and interactions between characters in a storyline

    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
    674
    +0.24
    0.7%
    2015
    +0.11
    0.3%
    906
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.24
    0.03
    1415
    +0.11
    0.02
    1470
    +0.11
    0.03
    Negative Logits
     optik
    -1.08
     akut
    -0.93
     silikon
    -0.91
     alkoh
    -0.91
     kosme
    -0.91
     antik
    -0.89
     makro
    -0.88
     lele
    -0.84
     kask
    -0.83
     gend
    -0.83
    POSITIVE LOGITS
    <bos>
    1.79
    Cześć
    0.53
     scoper
    0.53
     welkom
    0.52
    Dziękuję
    0.52
     zprávy
    0.51
     mwenye
    0.51
     úplně
    0.51
    sphase
    0.50
     fazia
    0.49
    Activations Density 0.232%

    No Known Activations