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. 183
    Prev
    Next
    INDEX
    Explanations

    information related to requirements for physical activity and software development

    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
    198
    +0.19
    0.6%
    1842
    +0.13
    0.4%
    468
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.19
    0.07
    1241
    +0.13
    0.05
    766
    +0.10
    0.05
    Negative Logits
    PerformLayout
    -0.69
    )}}{
    -0.68
    ])*
    -0.63
    ])):
    -0.63
    Apesar
    -0.62
    GOTREF
    -0.60
    ])))
    -0.60
    EventQueue
    -0.59
    Aplicaciones
    -0.59
    ])),
    -0.58
    POSITIVE LOGITS
     ftu
    1.57
     fta
    1.53
     aen
    1.52
     fuf
    1.49
     milf
    1.46
     fup
    1.46
     poff
    1.45
     fte
    1.44
     secon
    1.43
     ftre
    1.42
    Activations Density 0.733%

    No Known Activations