INDEX

Explanations

instances of the word "that" followed by a specific context or action

oai_token-act-pair · gpt-3.5-turbo

multiple instances of the word "that" indicating conditional or hypothetical situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enegger

-0.89

apolis

-0.86

uador

-0.81

 pione

-0.78

acements

-0.78

IAS

-0.78

leeve

-0.77

igmatic

-0.75

pots

-0.75

endez

-0.75

POSITIVE LOGITS

 happens

1.43

 occurs

1.20

 translates

1.16

 happened

1.06

 entails

0.99

 applies

0.99

 sounds

0.95

 means

0.95

 implies

0.94

 proves

0.93

Activations Density 0.105%

instances of the word "that" followed by a specific context or action

multiple instances of the word "that" indicating conditional or hypothetical situations

No Comments

No Known Activations