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. 991
    Prev
    Next
    INDEX
    Explanations

    references to the dangers of smoking and its consequences for public health

    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
    +0.32
    1.2%
    198
    +0.15
    0.6%
    1253
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.32
    0.07
    1445
    +0.15
    0.07
    1253
    +0.13
    0.04
    Negative Logits
    <bos>
    -2.46
    Билгалдахарш
    -0.69
     resourceCulture
    -0.63
    PerformLayout
    -0.60
     المعيارى
    -0.59
    InitStruct
    -0.57
     ProtoMessage
    -0.56
    msgTypes
    -0.56
    ⓧ
    -0.55
    ModelSerializer
    -0.53
    POSITIVE LOGITS
     bandung
    1.09
     soulign
    1.07
     véhic
    1.05
     Banjar
    1.02
     affor
    1.02
     Bekasi
    1.01
     Karang
    1.00
     flyknit
    1.00
     Pekan
    0.98
     Manufact
    0.98
    Activations Density 0.630%

    No Known Activations