INDEX

Explanations

mention of people associated with news articles or photographs

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

脚注の使い方

-1.02

saraba

-1.00

AndEndTag

-0.93

AddTagHelper

-0.89

 AssemblyCulture

-0.80

 consultato

-0.79

 ویکی‌پدیا

-0.78

 ProtoMessage

-0.76

 propOrder

-0.76

原始内容存档于

-0.75

POSITIVE LOGITS

Photo

0.55

photo

0.53

 photo

0.50

 fotógrafo

0.49

 photographer

0.47

 Photo

0.47

ساء

0.46

Photos

0.46

UTERS

0.45

 image

0.44

Activations Density 0.086%

mention of people associated with news articles or photographs

No Comments

No Known Activations