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. 15476
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to skills acquisition and development

    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
    1482
    +0.15
    0.6%
    1870
    +0.14
    0.5%
    2004
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.15
    0.03
    1482
    +0.14
    0.03
    2004
    +0.12
    0.02
    Negative Logits
     indestru
    -0.60
     disgra
    -0.56
     Maxime
    -0.54
     pessi
    -0.53
     Daria
    -0.53
     OnTrigger
    -0.53
     bambou
    -0.53
     Valentín
    -0.52
     philanth
    -0.52
     Rober
    -0.52
    POSITIVE LOGITS
     skills
    1.38
     skill
    1.36
    skills
    1.29
     Skills
    1.27
     Skill
    1.27
    skill
    1.25
    Skills
    1.22
    Skill
    1.22
     SKILLS
    1.15
    skilled
    0.90
    Activations Density 0.064%

    No Known Activations