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. 3082
    Prev
    Next
    INDEX
    Explanations

    information related to salaries, especially for software engineers in Seattle

    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
    1177
    +0.13
    0.4%
    1253
    +0.11
    0.3%
    1385
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1031
    +0.13
    0.04
    621
    +0.11
    0.03
    1880
    +0.10
    0.04
    Negative Logits
     hek
    -1.10
     kram
    -1.06
     lele
    -1.02
     logis
    -0.97
     kras
    -0.96
     adal
    -0.96
     plak
    -0.95
     bera
    -0.95
     krab
    -0.90
     reger
    -0.90
    POSITIVE LOGITS
     average
    0.81
    Average
    0.75
    average
    0.74
     Average
    0.73
     typical
    0.69
    avg
    0.68
    Avg
    0.66
     averages
    0.66
     Typical
    0.64
    Typical
    0.60
    Activations Density 0.330%

    No Known Activations