INDEX

Explanations

occurrences of the word "on."

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

acek

-0.54

kháu

-0.54

berdayakan

-0.52

صبحت

-0.52

дол

-0.50

 zewnętrzne

-0.49

 Theodo

-0.49

īj

-0.48

δή

-0.48

iramente

-0.48

POSITIVE LOGITS

 nahilalakip

0.71

Vidite

0.70

 "..\..\..\

0.66

yntaxException

0.62

 "..\..\

0.60

 createSlice

0.60

resave

0.57

цезда

0.56

 bearbeitet

0.56

 AspNetCore

0.56

Activations Density 0.132%

occurrences of the word "on."

No Comments

No Known Activations