© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 148
    Prev
    Next
    INDEX
    Explanations

    acronyms related to organizations or fields of study, specifically with a strong focus on the term "ECVDI"

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.13
    0.6%
    1265
    +0.07
    0.3%
    82
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    805
    +0.13
    0.06
    1265
    +0.07
    0.05
    511
    +0.06
    0.04
    Negative Logits
    <bos>
    -2.24
    ,
    -0.87
     would
    -0.86
     could
    -0.85
     have
    -0.82
     and
    -0.82
     can
    -0.82
     will
    -0.81
     has
    -0.80
    .
    -0.80
    POSITIVE LOGITS
     wien
    1.99
     stockholm
    1.97
     squa
    1.93
     mef
    1.88
     maneu
    1.88
     embodi
    1.82
     emphat
    1.81
     lidl
    1.77
     increa
    1.76
     unden
    1.76
    Activations Density 0.238%

    No Known Activations