INDEX

Explanations

phrases or words containing hyphens, specifically focusing on negative connotations

oai_token-act-pair · gpt-3.5-turbo

references to large-scale entities or phenomena

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

 Shutterstock

-0.85

 Powell

-0.72

issance

-0.70

 Scrib

-0.69

Wiz

-0.67

atche

-0.67

tsky

-0.65

jri

-0.64

 STATS

-0.63

 Cambodia

-0.63

POSITIVE LOGITS

bodied

1.25

enough

1.14

sized

1.13

scale

1.06

capacity

1.04

hearted

0.98

eyed

0.96

sounding

0.95

minded

0.92

sided

0.91

Activations Density 0.072%

phrases or words containing hyphens, specifically focusing on negative connotations

references to large-scale entities or phenomena

No Comments

No Known Activations