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. 139
    Prev
    Next
    INDEX
    Explanations

    scientific research data related to various disciplines and studies

    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
    906
    +0.15
    0.5%
    1343
    +0.14
    0.4%
    924
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    924
    +0.15
    0.03
    1804
    +0.14
    0.03
    283
    +0.13
    0.01
    Negative Logits
     McLaugh
    -1.03
     tupperware
    -1.00
     unlaw
    -0.93
     ecru
    -0.88
     Vaugh
    -0.88
     McInt
    -0.87
     swarovski
    -0.83
     cushi
    -0.81
     Daven
    -0.79
    Xoxo
    -0.73
    POSITIVE LOGITS
     Bakter
    0.59
     marte
    0.58
     BIBSYS
    0.54
     CiNii
    0.54
     fré
    0.53
    NSUserDefaults
    0.53
    Lengths
    0.53
    Declarations
    0.53
    Domains
    0.53
     PLWABN
    0.52
    Activations Density 0.078%

    No Known Activations