INDEX

Explanations

comparisons or quantities involving the word "than"

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing "more than" or comparative quantities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

adian

-0.71

NEY

-0.71

owe

-0.68

DH

-0.68

Interstitial

-0.68

ilic

-0.67

ensis

-0.67

culosis

-0.66

EMENT

-0.65

ä½¿

-0.65

POSITIVE LOGITS

 doubling

0.74

etheless

0.73

0.72

0.70

whelming

0.69

atos

0.68

0.67

 doubled

0.65

0.64

Activations Density 0.042%

comparisons or quantities involving the word "than"

phrases emphasizing "more than" or comparative quantities

No Comments

No Known Activations