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. 8333
    Prev
    Next
    INDEX
    Explanations

    organizations and associations, specifically mentioned with formal titles and names

    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
    227
    +0.15
    0.5%
    814
    +0.12
    0.4%
    663
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.15
    0.05
    156
    +0.12
    0.03
    1352
    +0.11
    0.04
    Negative Logits
    Hahah
    -0.95
     friable
    -0.94
     effe
    -0.93
    Ehh
    -0.93
     tetrach
    -0.93
    Hahahahaha
    -0.90
     desir
    -0.90
     unden
    -0.88
     ecru
    -0.87
     erec
    -0.86
    POSITIVE LOGITS
     Association
    1.22
     association
    1.14
    Association
    1.11
     associations
    0.96
    association
    0.95
     Associations
    0.94
     ASSOCIATION
    0.86
    assoc
    0.70
     Assn
    0.69
    associations
    0.68
    Activations Density 0.161%

    No Known Activations