INDEX

Explanations

phrases involving personal pronouns and requests for assistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

XmlAccessType

-0.66

setAccessible

-0.65

########.

-0.62

adpleegd

-0.60

ัพท์

-0.57

onViewCreated

-0.57

LookAnd

-0.57

 خارجية

-0.56

djangoproject

-0.56

évaluateur

-0.55

POSITIVE LOGITS

 showing

1.09

showing

1.02

 Showing

1.01

 shows

1.00

shows

0.99

 SHOWS

0.98

 Shows

0.97

Shows

0.97

shown

0.96

 shown

0.94

Activations Density 0.177%

phrases involving personal pronouns and requests for assistance

No Comments

No Known Activations