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. 1629
    Prev
    Next
    INDEX
    Explanations

    terms related to illicit drugs

    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
    1896
    +0.12
    0.4%
    478
    +0.12
    0.4%
    1328
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.12
    0.04
    505
    +0.12
    0.01
    468
    +0.12
    0.03
    Negative Logits
     déliv
    -0.70
     piú
    -0.69
     NSCoder
    -0.69
     augus
    -0.68
     pét
    -0.66
     gius
    -0.66
     Normdatei
    -0.65
     rédig
    -0.65
     quelcon
    -0.64
     pleins
    -0.64
    POSITIVE LOGITS
     initData
    0.59
     cocaine
    0.56
     ammunition
    0.52
     gasoline
    0.52
     distribution
    0.51
     heroin
    0.51
    anoia
    0.49
     getUsers
    0.48
     [''
    0.48
     electricity
    0.48
    Activations Density 0.222%

    No Known Activations