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. 15304
    Prev
    Next
    INDEX
    Explanations

    words related to news events and possible controversial political statements

    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
    528
    +0.10
    0.3%
    667
    +0.10
    0.3%
    411
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    667
    +0.10
    0.03
    1140
    +0.10
    0.03
    353
    +0.09
    0.03
    Negative Logits
    </h2>
    -0.51
    </h3>
    -0.49
    </strong>
    -0.48
    OW
    -0.47
    ↵↵
    -0.47
    }{
    -0.47
     .
    -0.47
    -
    -0.46
    0
    -0.46
    ↵
    -0.46
    POSITIVE LOGITS
     thut
    1.15
     Souha
    1.13
     fta
    1.12
     Juf
    1.11
     aen
    1.10
     Khart
    1.08
     fortn
    1.07
     dises
    1.07
     Adieu
    1.07
     squa
    1.05
    Activations Density 0.115%

    No Known Activations