INDEX

Explanations

names of people, places, and institutions relevant to achievements and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

ImageContext

-0.92

 protoimpl

-0.91

 tartalomajánló

-0.77

Datuak

-0.76

 myſelf

-0.73

 autorytatywna

-0.72

hyrchwyd

-0.71

 Jefus

-0.69

setVerticalGroup

-0.69

expandindo

-0.68

POSITIVE LOGITS

횟

0.47

ne

0.44

osphere

0.41

</strong>

0.40

den

0.39

Ob

0.39

acon

0.39

 concor

0.38

 stability

0.38

Activations Density 1.508%

names of people, places, and institutions relevant to achievements and events

No Comments

No Known Activations