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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15436
    Prev
    Next
    INDEX
    Explanations

    word pairs related to technical or legal concepts, specifically with a focus on "part" or "partial."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    680
    +0.12
    0.4%
    1480
    +0.10
    0.3%
    1339
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1480
    +0.12
    0.03
    680
    +0.10
    0.02
    1351
    +0.09
    0.02
    Negative Logits
    chaik
    -0.53
    LookAnd
    -0.48
     espé
    -0.47
     bross
    -0.47
     bren
    -0.45
     contemporánea
    -0.45
     végétal
    -0.45
     Cerca
    -0.45
     Viene
    -0.44
     confé
    -0.44
    POSITIVE LOGITS
     partial
    0.94
     Partial
    0.81
     partially
    0.80
    partial
    0.78
    Partial
    0.76
    partials
    0.67
     Partially
    0.66
     partly
    0.65
     parcial
    0.62
    Parti
    0.61
    Activations Density 0.117%

    No Known Activations