INDEX

Explanations

phrases indicating knowledge or information

oai_token-act-pair · gpt-3.5-turbo

the phrase "that" in various contexts

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

orah

-0.79

hens

-0.73

ãĥ¼ãĤ¯

-0.72

obb

-0.71

amia

-0.66

orian

-0.65

tails

-0.64

ield

-0.64

apolis

-0.62

estern

-0.61

POSITIVE LOGITS

 pesky

1.02

cher

0.76

 they

0.75

 there

0.75

 although

0.71

same

0.70

 fateful

0.70

 whereas

0.70

 someday

0.68

 THEY

0.67

Activations Density 0.203%

phrases indicating knowledge or information

the phrase "that" in various contexts

No Comments

No Known Activations