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. 8232
    Prev
    Next
    INDEX
    Explanations

    adjectives conveying negative evaluations

    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
    1265
    +0.14
    0.5%
    468
    +0.13
    0.4%
    188
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.14
    0.06
    188
    +0.13
    0.05
    1363
    +0.12
    0.05
    Negative Logits
    solicited
    -0.49
     interessanti
    -0.47
     scoper
    -0.47
    Perché
    -0.46
    -------
    
    -0.45
    Preço
    -0.44
    authorised
    -0.44
    warran
    -0.43
     buone
    -0.43
     riguard
    -0.42
    POSITIVE LOGITS
     marseille
    0.84
     cannes
    0.80
     carrefour
    0.80
     marte
    0.80
     wretch
    0.80
     popoli
    0.80
     cristi
    0.77
     fuo
    0.76
     cabrio
    0.76
     bourg
    0.75
    Activations Density 0.246%

    No Known Activations