INDEX

Explanations

occurrences of the verb "use" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 were

-0.49

ayant

-0.46

 weren

-0.45

 contact

-0.42

슷

-0.42

 כן

-0.41

were

-0.41

 могли

-0.40

 mean

-0.40

vités

-0.40

POSITIVE LOGITS

 sells

1.50

 sends

1.49

 learns

1.46

 wears

1.45

 receives

1.44

 develops

1.44

 celebrates

1.42

 takes

1.40

 marries

1.40

 collects

1.38

Activations Density 1.101%

occurrences of the verb "use" and its variations in context

No Comments

No Known Activations