INDEX

Explanations

expressions of ability or potential

oai_token-act-pair · gpt-3.5-turbo

phrases indicating user capabilities and functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Īè

-0.79

gling

-0.74

 Bearing

-0.74

abiding

-0.73

GGGGGGGG

-0.70

stood

-0.70

MpServer

-0.69

esting

-0.68

çĶŁ

-0.68

ausible

-0.68

POSITIVE LOGITS

 customize

1.42

 browse

1.22

 specify

1.20

 toggle

1.16

 choose

1.12

 anonymously

1.07

 configure

1.06

 upload

1.05

 edit

1.04

 visualize

1.04

Activations Density 0.135%

expressions of ability or potential

phrases indicating user capabilities and functionalities

No Comments

No Known Activations