INDEX

Explanations

strongly emphasized adjectives and phrases indicating influence or impact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 Paglinawan

-0.58

ArgsConstructor

-0.57

NoSuchAlgorithm

-0.57

 Prestige

-0.56

曖昧さ回避

-0.55

 mystique

-0.54

 BorderRadius

-0.53

 conquerors

-0.52

Zuz

-0.51

 sonder

-0.51

POSITIVE LOGITS

("")]

0.81

 strongly

0.79

 heavily

0.73

'),

0.67

"):

0.67

"),

0.67

 asset

0.65

ksikon

0.64

 fortement

0.64

addGap

0.63

Activations Density 0.502%

strongly emphasized adjectives and phrases indicating influence or impact

No Comments

No Known Activations