INDEX

Explanations

interrogative and demonstrative pronouns, particularly "what"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

in

-0.47

for

-0.47

Id

-0.46

Altre

-0.44

vodu

-0.44

hoenix

-0.43

 teki

-0.42

for

-0.41

POSITIVE LOGITS

 CreateTagHelper

0.99

enumii

0.88

 المعيارى

0.85

WebVitals

0.75

enumi

0.73

saraba

0.70

 للمعارف

0.70

ValueStyle

0.70

SpringBootTest

0.67

kuuta

0.66

Activations Density 0.126%

interrogative and demonstrative pronouns, particularly "what"

No Comments

No Known Activations