INDEX

Explanations

comparative phrases indicating superiority or preference

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

 BoxDecoration

-0.72

IRUS

-0.59

bosity

-0.54

 Larkin

-0.53

linde

-0.53

isseur

-0.53

">//

-0.52

tlement

-0.52

SizeF

-0.51

teis

-0.50

POSITIVE LOGITS

 THAN

1.62

 than

1.45

Than

1.43

 Than

1.41

THAN

1.20

than

1.14

 než

1.04

 decât

1.02

 niż

1.01

än

0.96

Activations Density 0.096%

comparative phrases indicating superiority or preference

No Comments

No Known Activations