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. 10036
    Prev
    Next
    INDEX
    Explanations

    mentions of political polls

    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
    1573
    +0.16
    0.6%
    214
    +0.16
    0.6%
    663
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.16
    0.04
    1573
    +0.16
    0.04
    663
    +0.15
    0.04
    Negative Logits
     inder
    -0.68
     roth
    -0.67
     défa
    -0.66
     wien
    -0.65
     Gode
    -0.60
     pyram
    -0.60
     noel
    -0.59
     Freuden
    -0.59
     pascal
    -0.58
     Wirt
    -0.58
    POSITIVE LOGITS
     poll
    1.59
     Poll
    1.37
    poll
    1.35
     polls
    1.32
    Poll
    1.27
     polling
    1.20
     POLL
    1.08
     Polls
    1.07
     polled
    1.07
    POLL
    1.05
    Activations Density 0.055%

    No Known Activations