INDEX

Explanations

adverbs that intensify or qualify the degree of an action or attribute

oai_token-act-pair · gpt-3.5-turbo

adverbs that modify intensity or degree

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

 DRAG

-0.62

 Nurs

-0.60

 Pant

-0.59

Paw

-0.58

 rivalry

-0.58

ayan

-0.57

idious

-0.56

Kap

-0.56

 Difference

-0.56

 Analysis

-0.55

POSITIVE LOGITS

\\\\\\\\\\\\\\\\

0.86

falls

0.79

udes

0.76

habi

0.73

Ĥİ

0.72

ements

0.71

ersed

0.69

ifies

0.69

SourceFile

0.68

sle

0.67

Activations Density 0.273%

adverbs that intensify or qualify the degree of an action or attribute

adverbs that modify intensity or degree

No Comments

No Known Activations