INDEX

Explanations

words related to historical events or moments in time

oai_token-act-pair · gpt-3.5-turbo

references to time periods in the past

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

wagon

-0.68

rapnel

-0.67

 Franch

-0.66

hat

-0.65

atism

-0.63

govtrack

-0.63

Sharp

-0.62

utters

-0.60

Gun

-0.60

/#

-0.58

POSITIVE LOGITS

ebin

1.32

 tense

1.05

decade

0.88

ĸļ

0.80

 week

0.78

iche

0.75

orate

0.73

 incarnation

0.72

 month

0.71

 semester

0.70

Activations Density 0.022%

words related to historical events or moments in time

references to time periods in the past

No Comments

No Known Activations