INDEX

Explanations

pronouns and their corresponding references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 campana

-0.53

 amitié

-0.51

rungsseite

-0.51

 yearly

-0.50

 ThemeData

-0.50

 prêmio

-0.49

󠁿

-0.48

ihnachts

-0.48

raires

-0.48

displayquote

-0.47

POSITIVE LOGITS

 before

0.96

 befo

0.92

before

0.91

Before

0.86

 Before

0.86

BEFORE

0.82

 sebelum

0.81

 Sebelum

0.81

 antes

0.80

 voordat

0.80

Activations Density 0.077%

pronouns and their corresponding references

No Comments

No Known Activations