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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 6788
    Prev
    Next
    INDEX
    Explanations

    specific time-related references, particularly focusing on months and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.20
    0.8%
    776
    +0.15
    0.6%
    897
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.20
    0.06
    1267
    +0.15
    0.06
    332
    +0.12
    0.05
    Negative Logits
    <bos>
    -2.73
    GTCX
    -0.84
     uska
    -0.81
    šech
    -0.77
     GenerationType
    -0.76
    <!--[
    -0.76
    IonicModule
    -0.75
    ="#"><
    -0.75
    /*++
    -0.74
    WebControls
    -0.74
    POSITIVE LOGITS
     maneu
    2.38
     reluct
    2.32
     affor
    2.25
     increa
    2.24
     Juf
    2.22
     emphat
    2.18
     apprehen
    2.18
     disagre
    2.18
     impra
    2.13
     perfet
    2.11
    Activations Density 0.102%

    No Known Activations