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. 1549
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features of electronic devices, particularly focusing on resolution, refresh rate, and connectivity options

    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
    678
    +0.12
    0.4%
    1385
    +0.12
    0.4%
    1870
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1368
    +0.12
    0.02
    615
    +0.12
    0.01
    280
    +0.10
    0.02
    Negative Logits
     ویکی‌پدیای
    -0.68
     invokingState
    -0.65
     whofe
    -0.64
     bonté
    -0.63
     pamph
    -0.63
    MENAFN
    -0.63
    Nachdem
    -0.62
     Souha
    -0.59
    Havolalar
    -0.58
     Vainqueur
    -0.58
    POSITIVE LOGITS
     resolution
    0.56
    Opportun
    0.52
     HD
    0.51
    Manufact
    0.49
     resolutions
    0.47
    Resolution
    0.47
     RESOLUTION
    0.47
    Histology
    0.46
     Resolution
    0.46
     besta
    0.45
    Activations Density 0.089%

    No Known Activations