INDEX

Explanations

phrases or keywords introducing additional information or related topics

oai_token-act-pair · gpt-3.5-turbo

the phrase "Also Read" indicating additional content or recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

#$

-0.69

ision

-0.67

VERSION

-0.65

$$$$

-0.64

hoe

-0.62

essor

-0.62

clusively

-0.62

vironment

-0.61

"},"

-0.61

idis

-0.60

POSITIVE LOGITS

 noteworthy

1.12

 Read

0.95

 notable

0.94

 Known

0.93

 read

0.87

 known

0.87

 Called

0.86

 note

0.84

 included

0.84

 noticeable

0.82

Activations Density 0.062%

phrases or keywords introducing additional information or related topics

the phrase "Also Read" indicating additional content or recommendations

No Comments

No Known Activations