INDEX

Explanations

variations of the word "express" and its derivatives in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WindowConstants

-0.54

زيز

-0.51

cinogen

-0.48

assertEqual

-0.47

 parcs

-0.44

ɒ

-0.44

šení

-0.43

pearance

-0.43

 preciosas

-0.43

verket

-0.43

POSITIVE LOGITS

ément

0.88

Gambas

0.87

 EXPRESS

0.85

 disambiguazione

0.84

 themselves

0.81

EXPRESS

0.81

Portail

0.80

 itself

0.78

 expressions

0.77

 expr

0.77

Activations Density 0.105%

variations of the word "express" and its derivatives in various contexts

No Comments

No Known Activations