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. 1564
    Prev
    Next
    INDEX
    Explanations

    sequences related to time constraints and deadlines

    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
    674
    +0.11
    0.3%
    1042
    +0.09
    0.3%
    908
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    908
    +0.11
    0.02
    330
    +0.09
    0.03
    1169
    +0.08
    0.06
    Negative Logits
     Messieurs
    -1.22
     noss
    -1.16
     affor
    -1.15
     Mémoires
    -1.14
     applau
    -1.14
     excru
    -1.13
     Traité
    -1.13
     increa
    -1.11
     Sén
    -1.10
     embodi
    -1.09
    POSITIVE LOGITS
    間に
    0.73
     delay
    0.72
     late
    0.69
     missed
    0.67
     rushed
    0.65
     before
    0.65
     deadline
    0.64
     timing
    0.63
     prior
    0.63
     delaying
    0.62
    Activations Density 0.818%

    No Known Activations