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. 1676
    Prev
    Next
    INDEX
    Explanations

    sentences emphasizing immediate actions or events

    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
    405
    +0.13
    0.4%
    1265
    +0.13
    0.4%
    1272
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    405
    +0.13
    0.03
    1272
    +0.13
    0.03
    1222
    +0.11
    0.03
    Negative Logits
     guma
    -0.79
     pinak
    -0.62
     tanong
    -0.61
     loob
    -0.56
     kanya
    -0.54
     walang
    -0.54
     pama
    -0.53
     maraming
    -0.51
     essentiels
    -0.50
     ibang
    -0.50
    POSITIVE LOGITS
     immediate
    0.81
     immediately
    0.79
     Immediate
    0.78
     pamph
    0.77
     Immediately
    0.75
     IMMEDIATE
    0.74
    Immediately
    0.71
     immedi
    0.71
     dramatist
    0.70
    immediately
    0.69
    Activations Density 0.101%

    No Known Activations