INDEX

Explanations

the particle "to" 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

ſelves

-0.87

 contextLoads

-0.86

 pleaſure

-0.85

InjectAttribute

-0.81

Efq

-0.81

ſelf

-0.81

 ſtate

-0.81

 myſelf

-0.80

 whoſe

-0.80

 doubtnut

-0.78

POSITIVE LOGITS

 gonna

1.48

Gonna

1.21

 Gonna

1.18

 GONNA

1.18

gonna

1.12

 will

0.98

 WILL

0.82

 going

0.80

Will

0.79

will

0.78

Activations Density 0.038%

the particle "to" in various contexts

No Comments

No Known Activations