INDEX

Explanations

words related to opinions and discussions

oai_token-act-pair · gpt-3.5-turbo

phrases that include commas, indicating a list or additional information

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

robe

-0.86

ved

-0.76

uci

-0.75

cott

-0.72

uces

-0.68

rug

-0.68

uce

-0.67

iple

-0.67

ivery

-0.67

irc

-0.65

POSITIVE LOGITS

 namely

1.38

 albeit

1.25

 though

1.06

 although

1.01

huh

1.00

viz

0.96

 however

0.96

 insofar

0.93

 especially

0.89

eh

0.86

Activations Density 0.476%

words related to opinions and discussions

phrases that include commas, indicating a list or additional information

No Comments

No Known Activations