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. 2741
    Prev
    Next
    INDEX
    Explanations

    dates or days mentioned in a text

    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
    1671
    +0.12
    0.4%
    397
    +0.11
    0.4%
    1926
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1671
    +0.12
    0.05
    1926
    +0.11
    0.04
    1335
    +0.10
    0.04
    Negative Logits
    IonicModule
    -0.52
    birthDate
    -0.50
     Ottobre
    -0.47
    Дереккөздер
    -0.46
    expandindo
    -0.46
     porción
    -0.45
    SUD
    -0.45
    وردار
    -0.44
     Giugno
    -0.43
    ɵɵelementEnd
    -0.43
    POSITIVE LOGITS
    day
    1.17
     day
    1.15
    Day
    1.11
     DAY
    1.11
     Day
    1.11
    DAY
    1.07
    days
    0.89
     día
    0.82
     days
    0.79
     Days
    0.78
    Activations Density 0.142%

    No Known Activations