INDEX

Explanations

prepositions indicating direction or purpose

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

jména

-0.95

 ་་

-0.84

 iſt

-0.82

 itſelf

-0.80

 NDEBUG

-0.77

 ―――――

-0.74

 fubject

-0.73

StateChanged

-0.71

 Majefty

-0.70

jetbrains

-0.69

POSITIVE LOGITS

to

2.13

TO

1.52

To

1.40

To

1.34

to

1.30

 να

1.20

zu

1.05

到

1.04

DataTo

1.00

ל

0.97

Activations Density 1.161%

prepositions indicating direction or purpose

No Comments

No Known Activations

prepositions indicating direction or purpose

No Comments

No Known Activations