INDEX

Explanations

phrases indicating emphasis or importance

oai_token-act-pair · gpt-3.5-turbo

the word "especially" and its variations, indicating emphasis or significance on particular subjects or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

only

-0.71

atre

-0.68

lied

-0.67

item

-0.67

toggle

-0.67

é¾

-0.67

lations

-0.66

advertising

-0.66

Runner

-0.65

lying

-0.65

POSITIVE LOGITS

 susceptible

0.83

 considering

0.80

 noticeable

0.75

 geared

0.73

 vulnerable

0.72

 emphasized

0.71

 suited

0.71

 noteworthy

0.70

 rewarding

0.67

 appreciated

0.67

Activations Density 0.021%

phrases indicating emphasis or importance

the word "especially" and its variations, indicating emphasis or significance on particular subjects or situations

No Comments

No Known Activations