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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6914
    Prev
    Next
    INDEX
    Explanations

    actions related to requesting, providing, submitting, giving, and receiving information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.13
    0.5%
    690
    +0.12
    0.5%
    1150
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1107
    +0.13
    0.05
    690
    +0.12
    0.06
    1654
    +0.10
    0.05
    Negative Logits
    <bos>
    -3.38
    displayquote
    -0.68
    frastructure
    -0.68
    ///**
    -0.66
    IsContent
    -0.64
     voulais
    -0.63
    ViewImports
    -0.60
    Примеча
    -0.59
     serai
    -0.58
     Мексичка
    -0.58
    POSITIVE LOGITS
     maneu
    1.19
     blackpink
    1.09
     impra
    1.09
     genshin
    1.06
     pixar
    1.04
     disreg
    1.00
     outlander
    0.99
     hentai
    0.97
     hasbro
    0.96
     madonna
    0.94
    Activations Density 0.904%

    No Known Activations