INDEX

Explanations

negations or exceptions in the text

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

 endwhile

-0.61

 dedans

-0.56

Ape

-0.53

Abi

-0.51

InputBorder

-0.51

}*/

-0.50

 vaut

-0.49

)];

-0.49

얻

-0.49

 égard

-0.48

POSITIVE LOGITS

 propOrder

0.80

 excluding

0.73

AutoScaleMode

0.73

 NSCoder

0.70

SuppressMessage

0.69

StructEnd

0.68

excluding

0.67

excl

0.67

 excepting

0.65

 المعيارى

0.64

Activations Density 0.332%

negations or exceptions in the text

No Comments

No Known Activations