INDEX

Explanations

the word "an" followed by a number

oai_token-act-pair · gpt-3.5-turbo

instances of the article "an."

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

BLE

-0.75

stones

-0.67

hood

-0.66

 Regions

-0.65

âĸº

-0.64

 psychiat

-0.64

Best

-0.62

 signify

-0.62

 pupils

-0.62

 nests

-0.62

POSITIVE LOGITS

abolic

1.25

agram

1.06

cients

1.02

alogue

1.00

onym

0.99

aer

0.98

omal

0.97

alyses

0.93

omaly

0.92

ointed

0.91

Activations Density 0.287%

the word "an" followed by a number

instances of the article "an."

No Comments

No Known Activations