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. 8287
    Prev
    Next
    INDEX
    Explanations

    phrases related to finance and economics

    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
    1150
    +0.13
    0.4%
    872
    +0.09
    0.3%
    776
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2043
    +0.13
    0.05
    613
    +0.09
    0.06
    1150
    +0.09
    0.03
    Negative Logits
     swarovski
    -0.67
     pandan
    -0.67
     nutella
    -0.61
     fusible
    -0.59
     roux
    -0.58
     tupperware
    -0.57
     sulphuric
    -0.56
     cammino
    -0.55
     abito
    -0.55
     anhyd
    -0.54
    POSITIVE LOGITS
     interview
    0.67
    Zapraszamy
    0.63
     interviewer
    0.63
    település
    0.60
     interviewed
    0.60
    municipi
    0.59
    astéro
    0.57
     interviews
    0.57
    <bos>
    0.56
     Interview
    0.56
    Activations Density 0.490%

    No Known Activations