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. 8416
    Prev
    Next
    INDEX
    Explanations

    references to technical information such as numerical values, datasets, research methodology, and technical specifications

    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
    381
    +0.13
    0.4%
    484
    +0.12
    0.4%
    876
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.13
    0.04
    896
    +0.12
    0.03
    82
    +0.11
    0.03
    Negative Logits
     déclaré
    -0.57
     asyncio
    -0.57
    MethodManager
    -0.54
    leyebilirsiniz
    -0.53
     katkı
    -0.53
    PROTOBUF
    -0.53
    ArgumentParser
    -0.52
    ParseTree
    -0.51
     estratégico
    -0.51
    Ekster
    -0.51
    POSITIVE LOGITS
     abnorm
    0.96
     embodi
    0.94
     unil
    0.86
     inext
    0.86
     ananas
    0.85
     inappro
    0.83
     conspic
    0.83
     erec
    0.83
     intersti
    0.82
     suscepti
    0.82
    Activations Density 0.159%

    No Known Activations