INDEX

Explanations

expressions related to ability or possibility

oai_token-act-pair · gpt-3.5-turbo

phrases indicating capability or potential

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ELD

-0.71

bent

-0.67

soDeliveryDate

-0.65

Appearances

-0.64

Qaeda

-0.61

 Integrity

-0.61

quartered

-0.60

backer

-0.60

hat

-0.60

been

-0.60

POSITIVE LOGITS

 afford

1.30

 withstand

1.24

 muster

1.21

 cope

1.14

 achieve

1.05

 accomplish

1.05

 communicate

1.05

 convince

1.04

 ascertain

1.04

 discern

1.03

Activations Density 0.087%

expressions related to ability or possibility

phrases indicating capability or potential

No Comments

No Known Activations