INDEX

Explanations

phrases related to locations and events

oai_token-act-pair · gpt-3.5-turbo

prepositions and phrases indicating conditions or situations

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

quickShipAvailable

-0.83

 alone

-0.72

inventoryQuantity

-0.69

Hug

-0.66

 mates

-0.65

omers

-0.65

wcsstore

-0.65

 partName

-0.63

ctors

-0.63

itte

-0.60

POSITIVE LOGITS

tones

0.72

grave

0.71

ŃĶ

0.68

piring

0.66

between

0.64

addock

0.63

andon

0.63

gery

0.62

ģ«

0.62

shadow

0.62

Activations Density 0.418%

phrases related to locations and events

prepositions and phrases indicating conditions or situations

No Comments

No Known Activations