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. 1117
    Prev
    Next
    INDEX
    Explanations

    infinitive forms of verbs, specifically focusing on the word "to."

    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
    +0.37
    2.1%
    1334
    +0.17
    1.0%
    161
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1334
    +0.37
    0.11
    161
    +0.17
    0.09
    395
    +0.14
    0.09
    Negative Logits
    <bos>
    -3.10
    /**
    -0.81
    ⓧ
    -0.71
    SharedCtor
    -0.71
    <?
    -0.70
    toBeDefined
    -0.70
    /*
    -0.65
    ,
    -0.65
     Roskov
    -0.64
    SequentialGroup
    -0.64
    POSITIVE LOGITS
     maneu
    1.84
     impra
    1.82
     reluct
    1.78
     hcm
    1.74
     increa
    1.71
     stockholm
    1.70
     accla
    1.68
     Juf
    1.63
     jorge
    1.61
     affor
    1.61
    Activations Density 0.578%

    No Known Activations