INDEX

Explanations

phrases that emphasize ease of use and convenience in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Theſe

-0.56

νό

-0.47

 Normdatei

-0.47

 '*')

-0.46

 referrerpolicy

-0.45

bed

-0.45

 existem

-0.45

 ترم

-0.45

ulso

-0.45

POSITIVE LOGITS

__":

0.73

getWriter

0.69

wpi

0.66

}{@

0.65

AsUp

0.64

prepareStatement

0.60

setVerticalGroup

0.58

__":

0.58

__':

0.58

ToAction

0.58

Activations Density 0.265%

phrases that emphasize ease of use and convenience in various contexts

No Comments

No Known Activations