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. 769
    Prev
    Next
    INDEX
    Explanations

    dates in various formats

    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
    +0.18
    0.9%
    1705
    +0.10
    0.5%
    1870
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1856
    +0.18
    0.06
    86
    +0.10
    0.04
    297
    +0.10
    0.04
    Negative Logits
    <bos>
    -3.14
    contentLoaded
    -0.80
    InitStruct
    -0.79
    ⓧ
    -0.78
    AsUp
    -0.75
    bewerken
    -0.73
     Italijani
    -0.72
     &___
    -0.72
     esternos
    -0.71
    verwijspagina
    -0.68
    POSITIVE LOGITS
     affor
    1.87
     unwarran
    1.73
     maneu
    1.72
     increa
    1.71
     disagre
    1.71
     unspeak
    1.66
     sovere
    1.64
     reluct
    1.64
     lidl
    1.62
     excru
    1.61
    Activations Density 0.100%

    No Known Activations