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. 657
    Prev
    Next
    INDEX
    Explanations

    references to vehicles, particularly vans

    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
    946
    +0.12
    0.4%
    1013
    +0.10
    0.3%
    1819
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.12
    0.05
    908
    +0.10
    0.03
    1819
    +0.09
    0.06
    Negative Logits
     chrysler
    -1.12
     vectra
    -1.08
     hilux
    -1.06
     isuzu
    -1.04
     peugeot
    -1.03
     cabrio
    -1.01
     broder
    -1.00
     doman
    -0.98
     milano
    -0.97
     yaris
    -0.96
    POSITIVE LOGITS
     parked
    0.74
     equipped
    0.60
    __":
    
    0.55
     carrying
    0.54
     transport
    0.54
     rental
    0.54
     parking
    0.53
     loaded
    0.52
     vehicle
    0.52
     car
    0.51
    Activations Density 0.311%

    No Known Activations