INDEX

Explanations

references to drinking and consumption of beverages

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-0.97

)++;

-0.82

 Weldon

-0.81

]")]

-0.80

guson

-0.75

 Egli

-0.75

UserScript

-0.75

 Lesley

-0.75

modelBuilder

-0.75

 relève

-0.75

POSITIVE LOGITS

 drink

1.68

 drinks

1.61

 Drink

1.61

Drink

1.57

drink

1.45

 DRINK

1.43

drinks

1.38

 Drinks

1.36

Drinks

1.33

 drinking

1.27

Activations Density 0.069%

references to drinking and consumption of beverages

No Comments

No Known Activations