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. 408
    Prev
    Next
    INDEX
    Explanations

    mentions of political organizations and financial terms

    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
    227
    +0.14
    0.4%
    1150
    +0.11
    0.3%
    2034
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.14
    0.09
    507
    +0.11
    0.05
    1438
    +0.08
    0.04
    Negative Logits
     Walkover
    -1.11
     utop
    -1.03
     antropo
    -0.90
     desertcart
    -0.86
     prostitu
    -0.86
     lavander
    -0.82
     gesta
    -0.82
     solidar
    -0.81
     noten
    -0.81
     hipo
    -0.81
    POSITIVE LOGITS
     impra
    2.19
     disagre
    2.06
     hairc
    2.05
     indestru
    2.03
     affor
    2.02
     shenan
    2.01
     unspeak
    2.01
     reluct
    1.96
     milf
    1.95
     increa
    1.95
    Activations Density 0.573%

    No Known Activations