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. 250
    Prev
    Next
    INDEX
    Explanations

    information related to requests, questions, receiving, and correspondence

    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
    198
    +0.10
    0.3%
    1055
    +0.09
    0.2%
    946
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2001
    +0.10
    0.04
    1055
    +0.09
    0.04
    1418
    +0.09
    0.04
    Negative Logits
     affor
    -0.93
     snoopy
    -0.92
     tupperware
    -0.89
     scrat
    -0.87
     shenan
    -0.81
     strick
    -0.81
     Chapitre
    -0.80
     disagre
    -0.79
     perfet
    -0.77
     peppa
    -0.77
    POSITIVE LOGITS
     requests
    0.96
     inquiries
    0.79
     enquiries
    0.75
    requests
    0.72
     complaints
    0.70
     request
    0.70
     feedback
    0.66
     queries
    0.66
     submissions
    0.65
     Requests
    0.62
    Activations Density 0.330%

    No Known Activations