Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13319
    Prev
    Next
    INDEX
    Explanations

    words related to comparisons or explanations, especially highlighting contrasting ideas

    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
    776
    +0.13
    0.4%
    331
    +0.10
    0.3%
    370
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.13
    0.07
    316
    +0.10
    0.06
    624
    +0.10
    0.05
    Negative Logits
    “…”
    -0.63
     Mónica
    -0.57
     Compañ
    -0.56
    Allister
    -0.55
    Namara
    -0.54
    “……”
    -0.54
     Batam
    -0.53
     Cárdenas
    -0.53
     Áng
    -0.51
     Joaqu
    -0.51
    POSITIVE LOGITS
    there
    0.68
     there
    0.67
    THERE
    0.66
     THERE
    0.66
    There
    0.62
     There
    0.60
     appui
    0.54
    earcher
    0.53
    theres
    0.52
     bý
    0.49
    Activations Density 0.148%

    No Known Activations