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. 7781
    Prev
    Next
    INDEX
    Explanations

    references to magazine covers and notable figures in fashion

    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
    +0.35
    1.2%
    678
    +0.10
    0.3%
    1150
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    924
    +0.35
    0.04
    1150
    +0.10
    0.03
    1912
    +0.08
    0.03
    Negative Logits
    <bos>
    -1.50
     Février
    -0.79
     Octobre
    -0.75
    ⓧ
    -0.74
    /**
    -0.74
     Septembre
    -0.73
     Décembre
    -0.69
    DockStyle
    -0.68
     Juillet
    -0.68
     Juin
    -0.67
    POSITIVE LOGITS
     Cuer
    0.78
     magazine
    0.78
     Compañ
    0.76
     Alcalde
    0.74
     idolat
    0.73
     pym
    0.71
     Darío
    0.70
     article
    0.68
     Lucía
    0.67
     hacienda
    0.67
    Activations Density 0.567%

    No Known Activations