INDEX

Explanations

phrases starting with "to" that express opinion or intention

oai_token-act-pair · gpt-3.5-turbo

the word "to" and its various usages throughout the text

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

pict

-0.80

accompanied

-0.73

rieved

-0.70

 SERV

-0.66

*/(

-0.66

VERTISEMENT

-0.65

Introduced

-0.65

flight

-0.64

urgy

-0.64

 Printed

-0.63

POSITIVE LOGITS

 paraph

1.38

 reiterate

1.27

ilet

1.17

 quote

1.15

 summarize

1.14

 borrow

1.08

 complicate

1.04

 clarify

1.01

wered

0.99

 recap

0.99

Activations Density 0.062%

phrases starting with "to" that express opinion or intention

the word "to" and its various usages throughout the text

No Comments

No Known Activations