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. 8198
    Prev
    Next
    INDEX
    Explanations

    mentions of various historical figures, events, and novels

    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
    198
    +0.16
    0.6%
    1265
    +0.16
    0.6%
    281
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.16
    0.04
    281
    +0.16
    0.03
    1265
    +0.13
    0.03
    Negative Logits
     leçons
    -0.67
     négociations
    -0.60
     investissements
    -0.59
     émissions
    -0.58
     prochaines
    -0.57
     laim
    -0.56
    alnız
    -0.56
     inconvénients
    -0.55
     réunions
    -0.55
     débats
    -0.55
    POSITIVE LOGITS
     fta
    1.29
     ftu
    1.22
     vns
    1.21
     poff
    1.18
     fep
    1.11
     fup
    1.10
     ftre
    1.08
     reft
    1.06
     miu
    1.05
     fte
    1.05
    Activations Density 0.075%

    No Known Activations