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. 15263
    Prev
    Next
    INDEX
    Explanations

    information related to dangerous encounters with wildlife, specifically sharks

    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
    +0.16
    0.5%
    906
    +0.14
    0.4%
    690
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.16
    0.06
    736
    +0.14
    0.07
    422
    +0.12
    0.03
    Negative Logits
     circon
    -0.82
     RSSSF
    -0.81
     anse
    -0.81
     Février
    -0.80
     BIBSYS
    -0.79
     marte
    -0.78
     broder
    -0.77
     palab
    -0.76
     pól
    -0.76
     poichè
    -0.74
    POSITIVE LOGITS
     sightings
    0.67
     sighting
    0.62
     lamella
    0.61
     startled
    0.60
     spotted
    0.60
     poetical
    0.58
     deterred
    0.57
     undisturbed
    0.56
     attracted
    0.55
     repelled
    0.54
    Activations Density 0.460%

    No Known Activations