INDEX

Explanations

phrases about individuals in various contexts, particularly focusing on their actions and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

lide

-0.43

 unele

-0.39

tw

-0.39

lides

-0.38

しております

-0.38

tay

-0.38

hless

-0.38

sp

-0.37

素质

-0.36

bus

-0.36

POSITIVE LOGITS

anything

0.95

AndEndTag

0.93

Efq

0.92

Anything

0.92

anyone

0.90

UrlResolution

0.90

 Cualquier

0.90

anywhere

0.90

 anyone

0.89

Wherever

0.89

Activations Density 0.299%

phrases about individuals in various contexts, particularly focusing on their actions and relationships

No Comments

No Known Activations