INDEX

Explanations

phrases related to statistical data, particularly percentages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

談社

-1.02

Zeneca

-0.95

AutoScaleMode

-0.90

OGND

-0.88

nobyl

-0.87

Bk

-0.85

 Dundas

-0.83

emf

-0.83

hdi

-0.83

TintMode

-0.83

POSITIVE LOGITS

en

0.81

ness

0.80

ation

0.76

ations

0.75

ing

0.72

ment

0.71

0.70

 ciento

0.70

ią

0.70

ult

0.70

Activations Density 0.116%

phrases related to statistical data, particularly percentages

No Comments

No Known Activations