INDEX

Explanations

references to specific time periods in relation to events or occurrences

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "week" to indicate recent events or updates

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

vim

-0.67

bler

-0.67

itialized

-0.64

izoph

-0.64

ventus

-0.62

ership

-0.61

 Gems

-0.61

gary

-0.61

pend

-0.59

omething

-0.58

POSITIVE LOGITS

days

1.19

night

1.08

 afternoon

0.90

DAY

0.78

 morning

0.76

 evening

0.76

 mornings

0.75

 ç¥ŀ

0.71

atell

0.71

bush

0.70

Activations Density 0.051%

references to specific time periods in relation to events or occurrences

occurrences of the word "week" to indicate recent events or updates

No Comments

No Known Activations