INDEX

Explanations

phrases indicating negation

oai_token-act-pair · gpt-3.5-turbo

negations or phrases indicating uncertainty or lack of specification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tenance

-0.74

saf

-0.72

ãĤ£

-0.68

how

-0.67

ould

-0.66

leen

-0.65

Ô

-0.65

 manag

-0.65

ERG

-0.65

WAY

-0.63

POSITIVE LOGITS

 necessarily

1.20

 formally

1.12

 overtly

1.12

 explicitly

1.09

 outright

1.07

 directly

1.06

 definitive

1.02

 definitively

1.01

 exact

1.00

 conclusive

0.98

Activations Density 0.476%

phrases indicating negation

negations or phrases indicating uncertainty or lack of specification

No Comments

No Known Activations