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. 15955
    Prev
    Next
    INDEX
    Explanations

    instances of phrases starting with "on" followed by a number specific to the context

    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
    1124
    +0.12
    0.5%
    1828
    +0.12
    0.5%
    31
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1828
    +0.12
    0.06
    1124
    +0.12
    0.06
    31
    +0.12
    0.05
    Negative Logits
     Leurs
    -0.63
    viewWillAppear
    -0.57
    acherous
    -0.57
    Plusieurs
    -0.55
    sbereich
    -0.53
    seigneur
    -0.52
     Jusqu
    -0.52
     Plusieurs
    -0.52
     viewWillAppear
    -0.52
     deleteUser
    -0.51
    POSITIVE LOGITS
     On
    0.85
     ON
    0.84
    On
    0.84
     onor
    0.75
     récon
    0.74
    ON
    0.72
     compréhen
    0.71
     effray
    0.69
    on
    0.68
    isOn
    0.67
    Activations Density 0.213%

    No Known Activations