INDEX

Explanations

recurrent phrases emphasizing "all" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 scheme

-0.57

 device

-0.55

 Jacobsen

-0.53

 programme

-0.51

PageRoute

-0.47

oudou

-0.47

tispiece

-0.47

 Fiske

-0.46

 Jacobson

-0.46

젯

-0.46

POSITIVE LOGITS

All

1.30

All

1.27

all

1.21

ALL

1.07

setAll

1.02

all

0.98

ALL

0.97

 Semua

0.96

 semua

0.87

ReadAll

0.82

Activations Density 0.249%

recurrent phrases emphasizing "all" in various contexts

No Comments

No Known Activations