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. 15021
    Prev
    Next
    INDEX
    Explanations

    words related to international conflicts and diplomatic negotiations

    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
    75
    +0.11
    0.3%
    2041
    +0.08
    0.2%
    1485
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    809
    +0.11
    0.04
    75
    +0.08
    0.02
    837
    +0.07
    0.02
    Negative Logits
     impra
    -1.48
     reluct
    -1.41
     maneu
    -1.35
     increa
    -1.34
     affor
    -1.31
     shenan
    -1.24
     purcha
    -1.23
     wherea
    -1.22
     strick
    -1.21
     scrat
    -1.21
    POSITIVE LOGITS
     hornblende
    0.59
    cault
    0.55
    phorbia
    0.52
    phazard
    0.51
    diali
    0.50
     հղումներ
    0.50
    Jornal
    0.50
     wild
    0.50
     biotite
    0.49
    lapsingToolbar
    0.49
    Activations Density 0.254%

    No Known Activations