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. 8399
    Prev
    Next
    INDEX
    Explanations

    words related to research findings and discussions about various topics

    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
    1013
    +0.11
    0.3%
    1870
    +0.10
    0.3%
    382
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    109
    +0.11
    0.06
    468
    +0.10
    0.06
    1867
    +0.09
    0.05
    Negative Logits
     specialmente
    -0.99
     perciò
    -0.90
     chiaramente
    -0.89
     purtroppo
    -0.85
     solidar
    -0.85
     persino
    -0.83
     ideolog
    -0.83
     anzi
    -0.81
     rispond
    -0.81
     succede
    -0.78
    POSITIVE LOGITS
    .
    0.71
    ;
    0.66
    ,
    0.58
     maxSize
    0.57
    。
    0.54
     rval
    0.54
     and
    0.53
    <bos>
    0.52
     totalCount
    0.52
    ly
    0.52
    Activations Density 0.425%

    No Known Activations