© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 119
    Prev
    Next
    INDEX
    Explanations

    phrases related to clothing and body representation

    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
    394
    +0.16
    0.5%
    1978
    +0.13
    0.4%
    872
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1833
    +0.16
    0.04
    21
    +0.13
    0.03
    142
    +0.11
    0.03
    Negative Logits
    <bos>
    -1.87
     intersper
    -1.45
     milf
    -1.30
     shenan
    -1.29
     excru
    -1.26
     encomp
    -1.23
     depic
    -1.22
     hentai
    -1.22
     snoopy
    -1.21
     superintend
    -1.21
    POSITIVE LOGITS
     fras
    0.81
    ...»
    0.77
     marte
    0.74
     prostitu
    0.73
     palestra
    0.73
     Toilette
    0.72
     seksi
    0.72
     itali
    0.71
    商品説明
    0.70
     biblia
    0.70
    Activations Density 0.083%

    No Known Activations