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. 16077
    Prev
    Next
    INDEX
    Explanations

    numbers that are part of a sequence continued from the previous number

    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
    1343
    +0.29
    0.9%
    1870
    +0.13
    0.4%
    1871
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.29
    0.05
    403
    +0.13
    0.04
    523
    +0.09
    0.03
    Negative Logits
     “
    -0.61
     moment
    -0.58
     at
    -0.56
    ...
    -0.55
     фа
    -0.55
     (
    -0.54
    ковы
    -0.54
     "
    -0.54
     по
    -0.53
    Når
    -0.53
    POSITIVE LOGITS
     dises
    1.54
     quæ
    1.43
     aen
    1.38
     magis
    1.37
     meis
    1.37
     cæ
    1.36
     mef
    1.32
     fatis
    1.32
     sii
    1.32
     ananas
    1.31
    Activations Density 0.092%

    No Known Activations