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. 10-RES-JB
    6. 1192
    Prev
    Next
    INDEX
    Explanations

    the word "it" in various contexts

    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.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.31
    1.5%
    82
    +0.13
    0.6%
    1222
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.31
    0.12
    1222
    +0.13
    0.10
    528
    +0.12
    0.10
    Negative Logits
    <bos>
    -2.86
    ⓧ
    -0.75
    дивиду
    -0.63
    EndContext
    -0.60
    Autoritní
    -0.57
    Шо
    -0.56
    <?
    -0.54
    GEBURTSDATUM
    -0.53
    webElementXpaths
    -0.52
     monitore
    -0.51
    POSITIVE LOGITS
    ">/
    1.08
    ">...
    1.04
     hilux
    0.90
    :"-
    0.88
    ">“
    0.86
    ">:
    0.85
     chrysler
    0.82
     camry
    0.82
    ">.
    0.80
     soulign
    0.78
    Activations Density 0.398%

    No Known Activations