INDEX

Explanations

terms related to starting or initiating something, such as 'start', 'shot', 'upstart', and 'growth'

oai_token-act-pair · gpt-3.5-turbo

phrases related to movement or progression

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

ancial

-0.66

 pedigree

-0.61

aghan

-0.61

stock

-0.60

abre

-0.60

 ping

-0.59

aley

-0.56

addock

-0.55

 closest

-0.55

edin

-0.55

POSITIVE LOGITS

xual

1.05

xia

0.83

ments

0.81

iances

0.81

ctr

0.81

iveness

0.78

enment

0.76

terday

0.75

ction

0.73

ment

0.71

Activations Density 0.077%

terms related to starting or initiating something, such as 'start', 'shot', 'upstart', and 'growth'

phrases related to movement or progression

No Comments

No Known Activations