INDEX

Explanations

references to a specific entity or person named "Le."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

-0.57

setVerticalGroup

-0.54

 Almost

-0.52

 almost

-0.51

 identically

-0.49

Bibliografia

-0.49

ientôt

-0.48

PreferredItem

-0.48

 familières

-0.48

 Zwar

-0.48

POSITIVE LOGITS

antMatchers

0.54

 defaultstate

0.49

 оригіналу

0.48

 AssemblyCulture

0.46

GTCX

0.45

 GenerationType

0.45

Baron

0.45

eward

0.44

 oprot

0.44

 nozze

0.42

Activations Density 0.177%

references to a specific entity or person named "Le."

No Comments

No Known Activations