INDEX

Explanations

variations of the word "give"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 للمعارف

-1.07

Luong

-0.83

 ujednoznacz

-0.83

luiting

-0.77

 Marcos

-0.76

ţele

-0.76

Série

-0.74

 resourceCulture

-0.74

XmlAccessType

-0.74

 Bourgoin

-0.74

POSITIVE LOGITS

Give

2.43

 Give

2.39

give

2.36

 give

2.34

 GIVE

2.16

 gives

2.10

Giving

2.09

 Giving

2.08

 giving

2.07

giving

2.05

Activations Density 0.103%

variations of the word "give"

No Comments

No Known Activations