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. 15078
    Prev
    Next
    INDEX
    Explanations

    mentions of hardware in the context of technology and tech products

    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
    1870
    +0.16
    0.6%
    795
    +0.14
    0.5%
    1438
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.16
    0.02
    168
    +0.14
    0.02
    795
    +0.13
    0.02
    Negative Logits
     fortn
    -0.87
     pamph
    -0.75
     tsl
    -0.74
     Moslem
    -0.74
     unlaw
    -0.73
     Juf
    -0.73
     viciss
    -0.71
     accla
    -0.71
     berea
    -0.70
     philanth
    -0.69
    POSITIVE LOGITS
     hardware
    1.35
    hardware
    1.23
     Hardware
    1.12
    Hardware
    1.10
    硬件
    0.82
    HARDWARE
    0.79
    hw
    0.61
    HW
    0.58
    ngrx
    0.56
     dollari
    0.56
    Activations Density 0.069%

    No Known Activations