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. 13543
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or comparison between multiple elements

    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
    50
    +0.22
    0.7%
    678
    +0.09
    0.3%
    108
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.22
    0.12
    1959
    +0.09
    0.12
    394
    +0.09
    0.08
    Negative Logits
     tré
    -0.58
     trá
    -0.55
     sér
    -0.54
    <s>
    -0.54
     sexu
    -0.53
     Horizonte
    -0.53
     Wikimédia
    -0.52
    EOR
    -0.52
    urie
    -0.49
    vains
    -0.49
    POSITIVE LOGITS
     unspeak
    1.35
     indestru
    1.34
     shenan
    1.28
     reluct
    1.27
     unwarran
    1.26
     disagre
    1.25
     unlaw
    1.20
     uninten
    1.20
     ftu
    1.17
     impra
    1.16
    Activations Density 2.163%

    No Known Activations