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. 520
    Prev
    Next
    INDEX
    Explanations

    information related to sports teams, their management decisions, and player movements

    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
    1042
    +0.10
    0.3%
    344
    +0.09
    0.3%
    1905
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1501
    +0.10
    0.06
    1226
    +0.09
    0.04
    1084
    +0.09
    0.05
    Negative Logits
     embodi
    -1.43
     swarovski
    -1.06
     fluo
    -1.02
     erad
    -1.02
     suscep
    -1.01
     eyel
    -1.01
     cytoplas
    -1.01
     yves
    -1.00
     peppa
    -1.00
     impractica
    -0.98
    POSITIVE LOGITS
     panik
    0.80
     kosme
    0.78
     minimalis
    0.77
     offseason
    0.69
     kriminal
    0.69
     praktik
    0.68
     kapital
    0.66
     kooper
    0.64
     akade
    0.64
     kredit
    0.64
    Activations Density 0.488%

    No Known Activations