INDEX

Explanations

phrases related to actions or events

oai_token-act-pair · gpt-3.5-turbo

words related to "caution" or "warning."

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

geist

-0.87

 GOODMAN

-0.81

bucks

-0.79

lings

-0.77

quickShipAvailable

-0.69

DragonMagazine

-0.69

kaya

-0.69

Ô

-0.68

hyde

-0.67

ticket

-0.66

POSITIVE LOGITS

utes

1.12

ute

1.01

utions

0.99

ution

0.98

uter

0.94

esar

0.91

pping

0.91

ffe

0.89

ffer

0.88

ppy

0.87

Activations Density 0.011%

phrases related to actions or events

words related to "caution" or "warning."

No Comments

No Known Activations