INDEX

Explanations

terms related to light, rays, and optics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ssch

-0.85

ngdoc

-0.85

**************

-0.84

 pinulongan

-0.82

:])

-0.77

lcccccc

-0.76

="#"><

-0.75

iomanip

-0.75

lrrr

-0.75

sumoto

-0.74

POSITIVE LOGITS

ay

1.26

Poy

1.24

Koy

1.20

 Rays

1.18

AY

1.16

AY

1.15

tray

1.11

BAY

1.10

 Guay

1.07

ey

1.07

Activations Density 0.240%

terms related to light, rays, and optics

No Comments

No Known Activations