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. 1518
    Prev
    Next
    INDEX
    Explanations

    descriptions of a person's experiences with a particular routine or activity

    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
    876
    +0.08
    0.2%
    1753
    +0.08
    0.2%
    1799
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.08
    0.06
    1553
    +0.08
    0.05
    330
    +0.07
    0.02
    Negative Logits
     accla
    -1.64
     reluct
    -1.59
     shenan
    -1.55
     encomp
    -1.55
     maneu
    -1.53
     depic
    -1.51
     affor
    -1.51
     increa
    -1.50
     impra
    -1.45
     Intere
    -1.44
    POSITIVE LOGITS
     productivity
    0.80
     distractions
    0.78
     Normdatei
    0.76
    <bos>
    0.71
     concentration
    0.67
     distraction
    0.66
    productive
    0.66
    Географиясе
    0.64
    @[+][
    0.64
    ItemBackground
    0.64
    Activations Density 0.470%

    No Known Activations