INDEX

Explanations

elements of structured formats or patterns

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

 eventdata

-0.73

__':

-0.67

__":

-0.62

 bezeichneter

-0.60

-0.58

 JSTOR

-0.58

Glej

-0.58

}(),

-0.58

 xlink

-0.56

}}/>

-0.56

POSITIVE LOGITS

hoga

0.65

揄

0.65

orescence

0.63

IsMutable

0.63

wts

0.62

󠁴

0.62

 Fauna

0.61

ACCIÓN

0.60

 оригіналу

0.60

 IBOutlet

0.60

Activations Density 0.032%

elements of structured formats or patterns

No Comments

No Known Activations