INDEX

Explanations

references to uncertainty and risk in contexts involving personal stories or engaging narratives

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

or symbols followed by em dashes

np_acts-logits-general · gemini-2.0-flash

em dash separator

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/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.24.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

''

-1.36

.”—

-1.21

—-

-1.19

”—

-1.18



-1.16

〜

-1.13

ății

-1.13

'''

-1.09

.—

-1.08

"—

-1.08

POSITIVE LOGITS

–

2.88

 –,

1.68

 أيضاً

1.18

്‍

1.17

ায়

1.07

-,

1.06

ല്‍

1.06

راً

1.04

اً

1.04

ര്‍

1.03

Activations Density 0.426%

references to uncertainty and risk in contexts involving personal stories or engaging narratives

or symbols followed by em dashes

em dash separator

No Comments

No Known Activations

references to uncertainty and risk in contexts involving personal stories or engaging narratives

or symbols followed by em dashes

em dash separator

No Comments

No Known Activations