INDEX

Explanations

words and phrases indicating claims or statements of alleged events or circumstances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

and

-0.58

-0.57

-0.52

We

-0.49

we

-0.48

DECREF

-0.47

or

-0.46

\\

-0.45

-0.44

li

-0.44

POSITIVE LOGITS

 allegedly

1.11

parsedMessage

1.08

edly

1.07

 supposedly

1.03

 alleged

0.94

 reportedly

0.94

 purported

0.93

supposed

0.93

EDEFAULT

0.93

 supuestamente

0.93

Activations Density 0.226%

words and phrases indicating claims or statements of alleged events or circumstances

No Comments

No Known Activations