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. 16074
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of gaming items or upgrades

    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
    +0.18
    0.7%
    227
    +0.15
    0.5%
    1224
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.18
    0.04
    163
    +0.15
    0.01
    1804
    +0.13
    0.03
    Negative Logits
     bezeichneter
    -0.75
     hina
    -0.70
     makro
    -0.68
     hek
    -0.67
     kac
    -0.65
     uhr
    -0.64
     kran
    -0.63
     vola
    -0.63
     spek
    -0.62
     saar
    -0.62
    POSITIVE LOGITS
     ecru
    0.59
     lycra
    0.55
     Jusqu
    0.54
    IntoConstraints
    0.53
    Przyp
    0.52
     bangle
    0.52
     époux
    0.52
     paisley
    0.51
     Shakspeare
    0.51
     hairc
    0.51
    Activations Density 0.215%

    No Known Activations