INDEX

Explanations

phrases related to someone's past experiences or backgrounds, particularly focusing on various life roles or professions

oai_token-act-pair · gpt-3.5-turbo

the word "as" in a variety of contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ongyang

-0.74

aceae

-0.73

redits

-0.70

Â¨

-0.70

autions

-0.70

rous

-0.67

ombs

-0.67

jas

-0.65

raq

-0.65

gin

-0.64

POSITIVE LOGITS

pired

1.38

pires

1.27

 well

0.90

 part

0.90

ynchron

0.86

 teenager

0.85

piring

0.84

 mayor

0.81

 opposed

0.80

 deputy

0.80

Activations Density 0.130%

phrases related to someone's past experiences or backgrounds, particularly focusing on various life roles or professions

the word "as" in a variety of contexts

No Comments

No Known Activations