INDEX

Explanations

conditional phrases indicating potential outcomes or possibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

inephrine

-0.78

BOP

-0.72

помним

-0.71

ReusableCell

-0.70

unas

-0.69

 layui

-0.69

BIB

-0.68

Pew

-0.67

Tus

-0.67

 Lulu

-0.67

POSITIVE LOGITS

 could

2.27

could

2.15

 COULD

2.05

 Could

2.04

Could

2.00

 podría

1.50

 pourrait

1.48

 podrían

1.42

 poderia

1.40

 könnte

1.39

Activations Density 0.080%

conditional phrases indicating potential outcomes or possibilities

No Comments

No Known Activations