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. 14987
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or events

    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
    1602
    +0.13
    0.4%
    1325
    +0.12
    0.4%
    1983
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1325
    +0.13
    0.05
    569
    +0.12
    0.08
    690
    +0.12
    0.04
    Negative Logits
     silikon
    -0.61
     conferir
    -0.60
     ekster
    -0.59
     clicar
    -0.59
     kriminal
    -0.58
     algu
    -0.58
     poliuret
    -0.58
     reconnaît
    -0.58
     ideolog
    -0.57
    Kä
    -0.57
    POSITIVE LOGITS
     hairc
    1.25
     inext
    1.21
     madonna
    1.13
     pegasus
    1.12
     swarovski
    1.12
     outlander
    1.10
     jurassic
    1.10
     ecru
    1.10
     snoopy
    1.08
     impra
    1.08
    Activations Density 0.751%

    No Known Activations