INDEX

Explanations

questions starting with the word "What"

oai_token-act-pair · gpt-3.5-turbo

questions beginning with "What."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ped

-0.67

por

-0.65

roads

-0.64

eer

-0.63

rod

-0.62

lot

-0.62

ulic

-0.61

gal

-0.61

Gy

-0.61

uttering

-0.60

POSITIVE LOGITS

soever

1.29

 happens

1.11

 happened

1.03

 distinguishes

0.94

 transpired

0.94

 happ

0.92

 kinds

0.87

 Lies

0.85

 sorts

0.84

 else

0.84

Activations Density 0.092%

questions starting with the word "What"

questions beginning with "What."

No Comments

No Known Activations