INDEX

Explanations

phrases related to awe or admiration

oai_token-act-pair · gpt-3.5-turbo

expressions related to awe or admiration, particularly the verb "behold."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

azines

-0.65

 Clinic

-0.64

red

-0.63

Ev

-0.60

ESC

-0.60

 strategies

-0.60

 comments

-0.60

ACS

-0.59

 suggested

-0.59

Pen

-0.59

POSITIVE LOGITS

 behold

4.41

 wedd

1.00

 unto

0.96

beh

0.93

 onlook

0.92

yea

0.84

 witnessing

0.84

 unprepared

0.80

nown

0.80

 unheard

0.79

Activations Density 0.014%

phrases related to awe or admiration

expressions related to awe or admiration, particularly the verb "behold."

No Comments

No Known Activations