INDEX

Explanations

terms related to authenticity and mobility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 PopupWindow

-0.57

 niti

-0.53

 PropTypes

-0.50

ViewById

-0.48

tldr

-0.48

igue

-0.48

crollView

-0.47

 simplified

-0.46

 rootReducer

-0.46

dif

-0.45

POSITIVE LOGITS

 globe

0.95

 legitimate

0.83

 Mobility

0.79

 Globe

0.79

 оригіналу

0.78

 genuine

0.78

 fate

0.77

 toss

0.76

globe

0.74

Mobility

0.74

Activations Density 0.075%

terms related to authenticity and mobility

No Comments

No Known Activations