INDEX

Explanations

descriptive terms related to food, particularly flavors and patient experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

RenderAtEndOf

-0.42

AddTagHelper

-0.41

verläs

-0.41

 Roskov

-0.37

 tight

-0.36

 ден

-0.34

savevideo

-0.34

 berço

-0.34

dealloc

-0.33

 endwhile

-0.33

POSITIVE LOGITS

 tastes

0.81

 taste

0.81

taste

0.68

 sensations

0.65

 Geschmack

0.63

 selera

0.62

 sensation

0.59

TypedDataSet

0.58

 tasted

0.58

 Taste

0.57

Activations Density 0.241%

descriptive terms related to food, particularly flavors and patient experiences

No Comments

No Known Activations