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. 2866
    Prev
    Next
    INDEX
    Explanations

    sports-related information, focusing on team names and player updates

    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
    1741
    +0.13
    0.4%
    1177
    +0.11
    0.3%
    736
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1965
    +0.13
    0.05
    648
    +0.11
    0.03
    632
    +0.09
    0.03
    Negative Logits
     Ottobre
    -1.03
     Settembre
    -1.00
     Luglio
    -0.98
     Giugno
    -0.96
     cammin
    -0.96
     particolar
    -0.91
     affez
    -0.90
     esplor
    -0.89
     sovra
    -0.86
     affitto
    -0.85
    POSITIVE LOGITS
    [])
    
    0.56
     panik
    0.54
    ’
    0.53
     disiplin
    0.51
    '
    0.51
     SPOILER
    0.50
    Xr
    0.50
     McLaugh
    0.49
     team
    0.49
    ][-
    0.48
    Activations Density 0.179%

    No Known Activations