INDEX

Explanations

hyphenated words, particularly those with a negative connotation

oai_token-act-pair · gpt-3.5-turbo

references to large-scale concepts or phenomena

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

issance

-0.69

 Shutterstock

-0.68

 Canaver

-0.68

 Powell

-0.67

 Curse

-0.65

nyder

-0.64

 advis

-0.64

 limbo

-0.63

 Scrib

-0.62

tsky

-0.60

POSITIVE LOGITS

bodied

1.32

scale

1.17

sized

1.08

enough

0.98

eyed

0.98

armed

0.91

capacity

0.91

hearted

0.91

unit

0.90

dollar

0.90

Activations Density 0.069%

hyphenated words, particularly those with a negative connotation

references to large-scale concepts or phenomena

No Comments

No Known Activations