INDEX

Explanations

word fragments, particularly names or terms with the letter sequence "yd"

oai_token-act-pair · gpt-3.5-turbo

the mention of locations, particularly cities and geographical references

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

========

-0.70

Ã§a

-0.67

 FIRE

-0.65

TAIN

-0.65

fully

-0.62

voy

-0.62

 deaf

-0.62

ãĥĪ

-0.61

Xi

-0.61

 pity

-0.60

POSITIVE LOGITS

aniel

1.13

ynamic

1.01

roid

0.97

ere

0.97

rox

0.96

essert

0.96

roxy

0.95

ynam

0.95

itions

0.94

elta

0.93

Activations Density 0.013%

word fragments, particularly names or terms with the letter sequence "yd"

the mention of locations, particularly cities and geographical references

No Comments

No Known Activations