INDEX

Explanations

phrases that start with "all of" followed by different contexts

oai_token-act-pair · gpt-3.5-turbo

phrases or sentences that contain the word "of."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

dayName

-0.82

illac

-0.68

atown

-0.63

 condem

-0.63

ertodd

-0.63

eele

-0.62

 subst

-0.62

 redesign

-0.59

 dictate

-0.59

 disposed

-0.58

POSITIVE LOGITS

 sorts

0.78

THING

0.77

 imaginable

0.70

ife

0.66

together

0.65

things

0.65

ources

0.65

onso

0.65

ahu

0.65

 sudden

0.64

Activations Density 0.066%

phrases that start with "all of" followed by different contexts

phrases or sentences that contain the word "of."

No Comments

No Known Activations