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. 2998
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal beliefs and values

    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
    50
    +0.19
    0.7%
    394
    +0.19
    0.6%
    1177
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.19
    0.15
    1415
    +0.19
    0.06
    468
    +0.13
    0.10
    Negative Logits
     susun
    -0.73
     sumpay
    -0.65
     marrone
    -0.63
     beginnetje
    -0.62
     дописавши
    -0.62
    Personensuche
    -0.58
     tanong
    -0.58
     silang
    -0.58
     trovo
    -0.57
    AddTagHelper
    -0.57
    POSITIVE LOGITS
    ”,
    0.59
    ",
    0.56
     prerog
    0.52
    ")
    0.52
    ").
    0.52
     despotism
    0.51
    "
    
    0.50
    ”)
    0.50
    "),
    0.50
    ”
    0.49
    Activations Density 3.694%

    No Known Activations