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. 728
    Prev
    Next
    INDEX
    Explanations

    instances where there is a mention of time or order within a series of actions

    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
    1013
    +0.15
    0.4%
    1535
    +0.12
    0.4%
    1842
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    202
    +0.15
    0.04
    273
    +0.12
    0.04
    1024
    +0.11
    0.04
    Negative Logits
     poichè
    -1.03
     increa
    -0.97
     Cfr
    -0.93
     »>
    -0.93
     Février
    -0.90
     fatis
    -0.89
     bourgeo
    -0.89
     affor
    -0.87
     unden
    -0.86
     lidl
    -0.85
    POSITIVE LOGITS
     proceedings
    0.61
     session
    0.61
     sessions
    0.58
     execution
    0.58
     transaction
    0.57
     transactions
    0.54
     rounds
    0.54
     mission
    0.50
     tasks
    0.49
     day
    0.49
    Activations Density 0.566%

    No Known Activations