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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 183
    Prev
    Next
    INDEX
    Explanations

    references to personal transformation and growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.37
    1.4%
    1013
    +0.18
    0.7%
    184
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.37
    0.15
    1317
    +0.18
    0.04
    2044
    +0.12
    0.14
    Negative Logits
    <bos>
    -1.68
     /**
    
    -0.72
    Geplaatst
    -0.63
    Autoritní
    -0.60
     CrossRef
    -0.58
     daf
    -0.56
     autorytatywna
    -0.55
     VD
    -0.55
     Tb
    -0.54
     CAI
    -0.54
    POSITIVE LOGITS
     pymysql
    0.92
     zove
    0.82
     myself
    0.79
     IOError
    0.78
    uerst
    0.75
     Bárbara
    0.75
     Hitam
    0.74
     smtplib
    0.74
     signora
    0.74
     IndexError
    0.74
    Activations Density 2.809%

    No Known Activations