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. 687
    Prev
    Next
    INDEX
    Explanations

    dates in various formats (month and day)

    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
    2034
    +0.11
    0.3%
    1150
    +0.09
    0.2%
    1537
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1750
    +0.11
    0.04
    1537
    +0.09
    0.04
    749
    +0.08
    0.03
    Negative Logits
     հղումներ
    -0.75
     himo
    -0.73
    : 
    -0.67
     nakalista
    -0.64
     Ause
    -0.63
     Ottobre
    -0.60
     podjela
    -0.59
    trás
    -0.59
     nawr
    -0.59
    omock
    -0.58
    POSITIVE LOGITS
     McInt
    1.19
     impra
    1.15
     disreg
    1.14
     McLaugh
    1.12
     unspeak
    1.06
     depic
    1.04
     maneu
    1.03
     Cuth
    1.02
     indestru
    1.01
     shenan
    1.01
    Activations Density 0.066%

    No Known Activations