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. 383
    Prev
    Next
    INDEX
    Explanations

    information related to computer hardware components, specifically GPUs (Graphics Processing Units) and chips

    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
    690
    +0.12
    0.4%
    478
    +0.10
    0.3%
    78
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    20
    +0.12
    0.02
    936
    +0.10
    0.02
    1798
    +0.09
    0.02
    Negative Logits
    <bos>
    -0.88
     pamph
    -0.63
     negroes
    -0.62
     Mónica
    -0.61
     blest
    -0.60
     Silurian
    -0.59
    descargar
    -0.57
    Примеча
    -0.56
    Ży
    -0.53
    findpost
    -0.52
    POSITIVE LOGITS
     daz
    0.74
     GPU
    0.73
     matel
    0.72
     fré
    0.70
     frambo
    0.68
     blos
    0.68
     GPUs
    0.68
     sopr
    0.68
    GPU
    0.67
     oreo
    0.67
    Activations Density 0.096%

    No Known Activations