INDEX

Explanations

words related to permanence or irreversible actions

oai_token-act-pair · gpt-3.5-turbo

terms associated with irreversibility and fundamental changes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

minster

-0.62

 Archangel

-0.60

 subconscious

-0.59

 lapse

-0.58

 reckoning

-0.58

è¦ļéĨĴ

-0.58

yip

-0.58

 Gaga

-0.57

 upwards

-0.57

 CLSID

-0.57

POSITIVE LOGITS

ishable

1.08

able

1.02

ables

0.98

enment

0.96

ably

0.92

ledged

0.92

vable

0.89

ibilities

0.88

ability

0.86

ptions

0.86

Activations Density 0.142%

words related to permanence or irreversible actions

terms associated with irreversibility and fundamental changes

No Comments

No Known Activations