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. 13811
    Prev
    Next
    INDEX
    Explanations

    phrases related to learning, teaching, and motivation

    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
    1150
    +0.14
    0.5%
    1870
    +0.11
    0.4%
    1510
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.14
    0.08
    2044
    +0.11
    0.07
    1380
    +0.09
    0.02
    Negative Logits
    Przyp
    -0.81
     apprehen
    -0.80
    Vaata
    -0.79
    Cechy
    -0.78
    Dlaczego
    -0.78
     specialmente
    -0.78
     emphat
    -0.77
    🕗
    -0.75
     reluct
    -0.75
    Solución
    -0.75
    POSITIVE LOGITS
    .
    0.73
    rousel
    0.63
    YARD
    0.62
     and
    0.62
    endetta
    0.62
    atibility
    0.60
     ElementRef
    0.60
    CAUTIONS
    0.59
    letterSpacing
    0.59
    medies
    0.58
    Activations Density 0.436%

    No Known Activations