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. 13999
    Prev
    Next
    INDEX
    Explanations

    mentions of specific selections or choices, such as those related to music labels, TV shows, or tournament participants

    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
    1758
    +0.16
    0.6%
    521
    +0.14
    0.5%
    849
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1758
    +0.16
    0.03
    521
    +0.14
    0.02
    1479
    +0.11
    0.02
    Negative Logits
     ***!
    -0.54
    TextFormField
    -0.50
    cambrian
    -0.44
     Campionato
    -0.43
     médaille
    -0.43
     Britton
    -0.42
    tamia
    -0.42
    InstrumentedTest
    -0.41
     Lordship
    -0.41
    LookAnd
    -0.41
    POSITIVE LOGITS
     selects
    1.13
     Selection
    1.12
     selection
    1.11
     selections
    1.10
     select
    1.08
     Select
    1.04
     selecting
    1.03
     Selecting
    1.01
     Selections
    1.01
     selected
    0.98
    Activations Density 0.068%

    No Known Activations