INDEX

Explanations

phrases indicating the end or outcome of an event

oai_token-act-pair · gpt-3.5-turbo

references to events or scenarios that result in an ending or conclusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 awoken

-0.66

Wee

-0.65

aird

-0.64

caster

-0.64

eph

-0.62

 differed

-0.62

tc

-0.61

itives

-0.60

 suited

-0.60

antam

-0.60

POSITIVE LOGITS

 tragedy

0.81

 dism

0.75

 humiliating

0.72

 tears

0.71

 Goodbye

0.71

 bankruptcy

0.70

 disappointment

0.69

 bloodshed

0.68

 mockery

0.67

 catastrophe

0.66

Activations Density 0.123%

phrases indicating the end or outcome of an event

references to events or scenarios that result in an ending or conclusion

No Comments

No Known Activations