INDEX

Explanations

words related to importance or significance

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

robe

-0.74

erv

-0.63

irie

-0.61

rose

-0.60

ongh

-0.59

 Ended

-0.56

stitial

-0.56

idy

-0.56

 Entered

-0.56

que

-0.56

POSITIVE LOGITS

 albeit

1.27

 especially

1.08

 although

1.04

 though

1.03

 however

1.03

 regardless

0.98

especially

0.97

 namely

0.95

albeit

0.95

 particularly

0.93

Activations Density 0.344%

words related to importance or significance

No Comments

No Known Activations