INDEX

Explanations

the word "every" and phrases that emphasize completeness or universality

oai_token-act-pair · gpt-3.5-turbo

instances of the word "every."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

phabet

-0.78

zai

-0.74

olas

-0.71

dict

-0.70

Osw

-0.68

 Metatron

-0.68

 Graves

-0.65

Viz

-0.62

Pru

-0.60

POST

-0.60

POSITIVE LOGITS

THING

1.52

 conceivable

1.26

 imaginable

1.19

where

1.11

single

1.00

 single

0.98

things

0.97

WHERE

0.86

 inch

0.85

thin

0.83

Activations Density 0.051%

the word "every" and phrases that emphasize completeness or universality

instances of the word "every."

No Comments

No Known Activations