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. 242
    Prev
    Next
    INDEX
    Explanations

    errors or issues related to punctuation, grammar, and formatting in text

    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
    1842
    +0.21
    0.6%
    1577
    +0.12
    0.4%
    184
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.21
    0.07
    1819
    +0.12
    0.09
    1363
    +0.11
    0.07
    Negative Logits
     dispen
    -1.93
     sappi
    -1.84
     embra
    -1.78
     socie
    -1.74
     ?...
    -1.71
     effe
    -1.71
     ordina
    -1.70
     ivi
    -1.68
     Perci
    -1.67
     doman
    -1.66
    POSITIVE LOGITS
     etc
    0.70
    relenting
    0.68
     и
    0.68
    出错
    0.66
     у
    0.66
     for
    0.65
     and
    0.65
    无效
    0.65
    效果
    0.64
    对于
    0.64
    Activations Density 0.701%

    No Known Activations