INDEX

Explanations

references to light and illumination contexts

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

 propOrder

-1.24

 bezeichneter

-1.02

ganu

-1.01

 оригіналу

-0.98

__":

-0.96

 ProtoMessage

-0.96

AndEndTag

-0.96

 FishBase

-0.93

quelize

-0.93

 تانيه

-0.92

POSITIVE LOGITS

 Light

1.56

 LIGHT

1.47

Light

1.46

light

1.42

 light

1.40

LIGHT

1.34

 Lightfoot

1.16

lights

1.08

 Lights

1.07

 Licht

1.04

Activations Density 0.086%

references to light and illumination contexts

No Comments

No Known Activations