INDEX

Explanations

phrases related to time

oai_token-act-pair · gpt-3.5-turbo

the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

fully

-0.70

uncle

-0.66

CLA

-0.66

wd

-0.65

 awaits

-0.64

.-

-0.63

EF

-0.63

wu

-0.63

 anew

-0.63

Enjoy

-0.63

POSITIVE LOGITS

 same

1.17

 latter

1.07

 entirety

1.03

 remainder

1.03

 entire

1.00

 rest

0.98

 proverbial

0.96

 whole

0.95

 widest

0.93

 slightest

0.90

Activations Density 0.250%

phrases related to time

the word "the."

No Comments

No Known Activations