INDEX

Explanations

adjectives that describe subtle variations in quantity or quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Hochspringen

-0.72

kal

-0.61

FetchType

-0.58

jPanel

-0.57

 life

-0.56

vi

-0.55

man

-0.55

ge

-0.55

randrange

-0.55

Mang

-0.54

POSITIVE LOGITS

slightly

1.84

Slight

1.83

Slightly

1.82

 Slightly

1.79

 slightly

1.78

 Slight

1.72

 slight

1.71

 légèrement

1.51

 leggermente

1.46

 ligeramente

1.44

Activations Density 0.116%

adjectives that describe subtle variations in quantity or quality

No Comments

No Known Activations