INDEX

Explanations

traits or features that set something apart or make it unique

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate how something is distinguished or differentiated from others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 commute

-0.75

onic

-0.74

aft

-0.71

 vomiting

-0.68

 spir

-0.65

stant

-0.64

 poisoning

-0.63

 numb

-0.63

 draining

-0.63

ancel

-0.63

POSITIVE LOGITS

ĸļ

1.07

 uniqueness

0.93

ortment

0.87

¥µ

0.80

iqueness

0.79

 excellence

0.78

 Achievement

0.78

 distinguishes

0.77

":"","

0.76

Orig

0.76

Activations Density 0.240%

traits or features that set something apart or make it unique

phrases that indicate how something is distinguished or differentiated from others

No Comments

No Known Activations