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. 8311
    Prev
    Next
    INDEX
    Explanations

    information related to a news article about teenagers involved in suspicious activities and legal proceedings

    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
    1539
    +0.09
    0.3%
    2016
    +0.08
    0.2%
    1601
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    513
    +0.09
    0.04
    1252
    +0.08
    0.05
    1504
    +0.08
    0.05
    Negative Logits
     asfal
    -0.59
     silikon
    -0.56
     morfo
    -0.55
     netto
    -0.54
     stoff
    -0.54
     balon
    -0.54
    Modèle
    -0.52
     rada
    -0.51
     tille
    -0.51
     Grecs
    -0.50
    POSITIVE LOGITS
     themselves
    0.80
    Their
    0.75
     Their
    0.70
    themselves
    0.70
     their
    0.68
    their
    0.67
     THEIR
    0.64
     thier
    0.63
     berea
    0.57
    krish
    0.54
    Activations Density 0.414%

    No Known Activations