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. 10093
    Prev
    Next
    INDEX
    Explanations

    phrases related to making decisions or assessments based on evidence and data

    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
    667
    +0.13
    0.5%
    528
    +0.13
    0.5%
    1994
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    667
    +0.13
    0.04
    1056
    +0.13
    0.03
    30
    +0.12
    0.03
    Negative Logits
     reluct
    -0.71
     contex
    -0.69
     inev
    -0.68
     embra
    -0.68
     depic
    -0.66
     disad
    -0.66
     impractica
    -0.66
     unlaw
    -0.65
     guarante
    -0.63
     Tanja
    -0.63
    POSITIVE LOGITS
     determination
    1.06
     determine
    1.05
     determined
    1.05
     determines
    1.00
    determine
    0.99
     determining
    0.96
    determined
    0.96
    determination
    0.96
     Determine
    0.94
     determin
    0.92
    Activations Density 0.066%

    No Known Activations