INDEX

Explanations

terms and phrases related to minimum thresholds or values, often in a scientific or technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 المعيارى

-0.65

>{@

-0.61

retVal

-0.60

epa

-0.59

sApp

-0.55

../../../

-0.55

ztály

-0.54

awe

-0.52

 Waray

-0.52

epa

-0.52

POSITIVE LOGITS

in

0.81

inn

0.70

IN

0.66

ining

0.66

ini

0.66

inna

0.64

lin

0.64

In

0.64

ino

0.61

Lin

0.60

Activations Density 0.800%

terms and phrases related to minimum thresholds or values, often in a scientific or technical context

No Comments

No Known Activations