INDEX

Explanations

names of people and their connections to events or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 consequently

-0.52

parametrize

-0.51

feldt

-0.51

 valign

-0.51

 nationale

-0.50

 accordingly

-0.49

τον

-0.49

ropia

-0.48

Encyclo

-0.48

 therefore

-0.48

POSITIVE LOGITS

WebElementEntity

0.76

deep

0.74

OGND

0.73

InputBorder

0.70

inflater

0.67

 BoxDecoration

0.66

inder

0.64

NameInMap

0.62

!*\

0.61

jeet

0.61

Activations Density 0.174%

names of people and their connections to events or roles

No Comments

No Known Activations