INDEX

Explanations

phrases related to events or actions coming to a conclusion

oai_token-act-pair · gpt-3.5-turbo

instances of the word "ended" or variations of it, indicating conclusions or closures

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

 Parables

-0.66

hee

-0.60

leted

-0.60

iard

-0.59

 broom

-0.56

pillar

-0.56

onne

-0.55

average

-0.55

esome

-0.54

è¦ļéĨĴ

-0.54

POSITIVE LOGITS

 abruptly

1.27

 prematurely

1.18

 tragically

1.08

 peacefully

1.02

angering

1.01

angers

0.98

eared

0.93

owment

0.85

 badly

0.85

orses

0.85

Activations Density 0.039%

phrases related to events or actions coming to a conclusion

instances of the word "ended" or variations of it, indicating conclusions or closures

No Comments

No Known Activations