INDEX

Explanations

specific time periods, particularly the prefix "early."

oai_token-act-pair · gpt-3.5-turbo

references to time periods labeled as "early" followed by numerical decades or years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

edIn

-0.89

dain

-0.76

ittee

-0.72

ortium

-0.71

shall

-0.70

channelAvailability

-0.70

avorite

-0.69

illary

-0.68

 presently

-0.68

uyomi

-0.66

POSITIVE LOGITS

 stages

1.03

 twenties

0.94

 phases

0.94

est

0.86

 days

0.83

-'

0.81

 prototypes

0.80

0.78

 morning

0.78

 versions

0.78

Activations Density 0.019%

specific time periods, particularly the prefix "early."

references to time periods labeled as "early" followed by numerical decades or years

No Comments

No Known Activations