INDEX

Explanations

modal verbs indicating possibility or likelihood

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

RTEX

-0.65

basicConfig

-0.59

énario

-0.55

YSTEM

-0.51

usermodel

-0.51

Dziękuję

-0.50

 DataLoader

-0.50

 lenker

-0.49

 hlavně

-0.48

{}",

-0.48

POSITIVE LOGITS

 well

1.13

 mắn

0.83

well

0.79

 possibly

0.77

haps

0.76

Well

0.75

#+#

0.73

hap

0.73

MigrationBuilder

0.73

 Well

0.72

Activations Density 0.176%

modal verbs indicating possibility or likelihood

No Comments

No Known Activations