INDEX

Explanations

references to specific names or entities

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

IBarButtonItem

-0.68

ModelSerializer

-0.66

 Walton

-0.65

Myers

-0.63

Raquel

-0.63

 Walden

-0.62

 Hickey

-0.61

principalColumn

-0.60

 Jara

-0.60

 EClass

-0.60

POSITIVE LOGITS

Vah

1.17

Lah

1.10

uh

1.05

Cah

1.04

mah

1.04

AH

1.04

Moh

1.04

lah

1.03

AH

1.03

wah

1.02

Activations Density 2.992%

references to specific names or entities

No Comments

No Known Activations