INDEX

Explanations

phrases related to a large quantity or number

oai_token-act-pair · gpt-3.5-turbo

references to large quantities or amounts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Springs

-0.75

DragonMagazine

-0.69

issance

-0.69

eer

-0.68

************

-0.64

tein

-0.64

 recol

-0.62

mable

-0.62

Topics

-0.62

 truce

-0.60

POSITIVE LOGITS

urus

0.98

ension

0.92

ory

0.89

urous

0.87

urers

0.85

ract

0.81

urgical

0.79

hest

0.79

ouls

0.79

urious

0.76

Activations Density 0.034%

phrases related to a large quantity or number

references to large quantities or amounts

No Comments

No Known Activations