INDEX

Explanations

occurrences of the word "text" in various contexts or forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

 Wicidata

-0.60

ValueStyle

-0.57

NullCheck

-0.56

]="

-0.55

 oprot

-0.53

-0.52

CPtr

-0.52

?>>

-0.52

-0.51

 vettoriale

-0.50

POSITIVE LOGITS

 purpoſe

0.86

 оригіналу

0.79

IMPORTED

0.77

wiſe

0.73

 houſe

0.73

ſelf

0.72

 ſtate

0.71

 leaſt

0.70

neſs

0.70

Tikang

0.69

Activations Density 0.002%

occurrences of the word "text" in various contexts or forms

No Comments

No Known Activations