Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2670
    Prev
    Next
    INDEX
    Explanations

    phrases related to diplomatic efforts and collapsed peace talks

    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
    344
    +0.12
    0.4%
    1499
    +0.12
    0.4%
    1598
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.12
    0.06
    309
    +0.12
    0.05
    652
    +0.09
    0.05
    Negative Logits
     swarovski
    -1.89
     hairc
    -1.86
     scrat
    -1.84
     indestru
    -1.83
     perfet
    -1.81
     snoopy
    -1.81
     hentai
    -1.74
     emphat
    -1.72
     impra
    -1.72
     cushi
    -1.72
    POSITIVE LOGITS
     negotiations
    0.92
     negotiation
    0.76
     talks
    0.74
    negoti
    0.73
    Negoti
    0.70
     negotiating
    0.66
    AutoScaleMode
    0.65
     Himo
    0.65
    GeneratedCode
    0.65
     negotiated
    0.65
    Activations Density 0.443%

    No Known Activations