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. 8292
    Prev
    Next
    INDEX
    Explanations

    words related to the internet and technology

    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
    553
    +0.13
    0.5%
    1677
    +0.13
    0.5%
    1306
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    553
    +0.13
    0.04
    1677
    +0.13
    0.03
    196
    +0.11
    0.03
    Negative Logits
    oretical
    -0.48
     zdrow
    -0.47
     gainera
    -0.47
    actylus
    -0.46
    agonal
    -0.45
     Referential
    -0.45
    GARET
    -0.43
    edback
    -0.43
     izvē
    -0.41
    눠
    -0.41
    POSITIVE LOGITS
    Internet
    1.24
     internet
    1.23
     Internet
    1.21
    internet
    1.19
     INTERNET
    1.05
    INTERNET
    0.88
     morire
    0.78
     Interne
    0.75
     credere
    0.71
     compréhen
    0.69
    Activations Density 0.063%

    No Known Activations