INDEX

Explanations

phrases related to specific names or terms such as "Pul"

oai_token-act-pair · gpt-3.5-turbo

references to a specific name or entity, likely associated with a notable figure or brand

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

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

schild

-0.91

enegger

-0.91

è¦ļéĨĴ

-0.80

 Generations

-0.78

 Remastered

-0.72

 Cellular

-0.71

 Hercules

-0.70

 Annotations

-0.68

 Butterfly

-0.66

 Echoes

-0.64

POSITIVE LOGITS

wyn

1.12

aya

0.99

ient

0.99

leen

0.98

vin

0.98

eston

0.96

keley

0.95

ush

0.94

sey

0.89

quet

0.88

Activations Density 0.041%

phrases related to specific names or terms such as "Pul"

references to a specific name or entity, likely associated with a notable figure or brand

No Comments

No Known Activations