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. 9244
    Prev
    Next
    INDEX
    Explanations

    information related to economic studies and academic backgrounds

    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
    1472
    +0.16
    0.8%
    1810
    +0.15
    0.8%
    892
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.16
    0.04
    1896
    +0.15
    0.03
    1741
    +0.13
    -0.01
    Negative Logits
    <bos>
    -1.18
    Demografía
    -0.80
    RTEX
    -0.79
    BagLayout
    -0.77
     NSCoder
    -0.73
    IContainer
    -0.71
     елның
    -0.70
    isContained
    -0.69
    GTCX
    -0.69
    Αν
    -0.68
    POSITIVE LOGITS
     impra
    1.63
     shenan
    1.61
     indestru
    1.61
     increa
    1.60
     maneu
    1.56
     alberto
    1.47
     affor
    1.47
     unspeak
    1.46
     Minang
    1.41
     depic
    1.39
    Activations Density 0.592%

    No Known Activations