© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 15168
    Prev
    Next
    INDEX
    Explanations

    phrases related to warmth and hospitality

    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
    1350
    +0.16
    0.6%
    347
    +0.16
    0.6%
    1491
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    347
    +0.16
    0.02
    1491
    +0.16
    0.03
    559
    +0.14
    0.02
    Negative Logits
     depic
    -0.74
     encomp
    -0.65
     volunte
    -0.65
     lts
    -0.64
     unden
    -0.61
     liquido
    -0.60
     prodi
    -0.60
     puto
    -0.60
     bascul
    -0.59
     ?...
    -0.59
    POSITIVE LOGITS
     warm
    1.35
     Warm
    1.28
    warm
    1.27
    Warm
    1.25
     WARM
    1.20
     warming
    1.20
     warmth
    1.17
     warms
    1.15
    warming
    1.11
    WARM
    1.09
    Activations Density 0.068%

    No Known Activations