INDEX

Explanations

phrases indicating a quantity or group of items

oai_token-act-pair · gpt-3.5-turbo

quantities and variations, particularly focusing on the words "few" and "numerous."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

istan

-0.85

ESE

-0.83

anwhile

-0.77

SPONSORED

-0.75

said

-0.73

ared

-0.72

Constructed

-0.71

ale

-0.70

ARS

-0.70

ARY

-0.70

POSITIVE LOGITS

 interesting

1.27

 surprises

1.18

 ways

1.05

 advantages

1.04

 modifications

1.04

 exciting

1.03

 useful

1.03

 variations

1.00

 notable

0.99

 noteworthy

0.99

Activations Density 0.197%

phrases indicating a quantity or group of items

quantities and variations, particularly focusing on the words "few" and "numerous."

No Comments

No Known Activations