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. 8328
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events and decisions that garner significant public attention

    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
    906
    +0.14
    0.4%
    108
    +0.13
    0.4%
    344
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.14
    0.04
    112
    +0.13
    0.02
    1501
    +0.10
    0.03
    Negative Logits
     recrystal
    -0.59
    nictwa
    -0.58
     rodzic
    -0.56
    STRUCTOR
    -0.53
    owników
    -0.52
    skiej
    -0.52
    maxWidth
    -0.51
     dziewczyn
    -0.50
    ską
    -0.50
    aduras
    -0.50
    POSITIVE LOGITS
     emphat
    1.25
     pamph
    1.21
     McLaugh
    1.19
     Abbé
    1.16
     depic
    1.15
     reluct
    1.13
     Keny
    1.12
     accla
    1.10
     Shakspeare
    1.08
     inconce
    1.07
    Activations Density 0.565%

    No Known Activations