© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 5884
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a sense of strong allure or desire

    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
    457
    +0.08
    0.2%
    674
    +0.07
    0.2%
    1166
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.08
    0.04
    301
    +0.07
    0.02
    371
    +0.07
    0.02
    Negative Logits
     disagre
    -1.19
     impra
    -1.06
     increa
    -1.02
     depic
    -1.00
     apprehen
    -1.00
     Simult
    -0.99
     Varan
    -0.99
     disgra
    -0.99
     resear
    -0.98
     excru
    -0.96
    POSITIVE LOGITS
     tempted
    1.25
     temptation
    1.20
     tempting
    1.18
     temptations
    0.85
     urge
    0.76
     tendency
    0.69
    tempt
    0.64
    calciatore
    0.60
     tempt
    0.60
     easy
    0.59
    Activations Density 0.307%

    No Known Activations