INDEX

Explanations

forms of the verb "to be"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 eorum

-0.77

 Mommy

-0.77

 habet

-0.76

 publiques

-0.74

 mirage

-0.74

 customization

-0.74

Tio

-0.73

 postIndex

-0.73

Biv

-0.73

antMatchers

-0.72

POSITIVE LOGITS

was

1.14

Was

1.08

WAS

1.08

Was

1.05

 Were

1.01

 WERE

1.01

Twas

1.00

 were

1.00

twas

0.95

was

0.88

Activations Density 0.530%

forms of the verb "to be"

No Comments

No Known Activations