Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8100
    Prev
    Next
    INDEX
    Explanations

    words related to political controversies, scandals, and consequences

    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
    604
    +0.10
    0.3%
    752
    +0.08
    0.2%
    1317
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.10
    0.05
    767
    +0.08
    0.03
    16
    +0.08
    0.06
    Negative Logits
    <bos>
    -1.18
    ngdoc
    -0.53
     CreateTagHelper
    -0.51
    AddTagHelper
    -0.50
    BagConstraints
    -0.48
    .*")]
    -0.48
     <>",
    -0.46
    "/",
    -0.46
    Etimo
    -0.45
    AddHtmlAttribute
    -0.45
    POSITIVE LOGITS
     Khart
    0.69
     Abbé
    0.67
     cushi
    0.66
    fordable
    0.65
     trefoil
    0.65
     carrefour
    0.64
     inext
    0.62
     nutella
    0.61
     jurassic
    0.61
     tucson
    0.60
    Activations Density 0.416%

    No Known Activations