INDEX

Explanations

affirmations and expressions of certainty or emphasis

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

adverbs or emphasis words

oai_token-act-pair · gpt-3.5-turbo

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

amins

-0.71

robe

-0.64

unts

-0.63

rencies

-0.63

 ILCS

-0.61

byter

-0.60

soDeliveryDate

-0.60

nea

-0.60

igans

-0.60

amina

-0.59

POSITIVE LOGITS

 whereby

0.91

of

0.77

 arises

0.67

about

0.66

between

0.64

 regarding

0.63

uristic

0.63

erie

0.62

that

0.62

Ī

0.62

Activations Density 0.554%

affirmations and expressions of certainty or emphasis

adverbs or emphasis words

No Comments

No Known Activations