INDEX

Explanations

references to time durations, particularly mentioning years and decades

oai_token-act-pair · gpt-3.5-turbo

references to time durations, particularly in years and months

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

 Hearts

-0.64

eus

-0.62

Haw

-0.62

alg

-0.62

Kid

-0.61

 subp

-0.60

inite

-0.60

Tau

-0.59

 Amph

-0.59

kind

-0.58

POSITIVE LOGITS

ago

1.10

 gestation

0.86

 elapsed

0.83

Ago

0.71

vable

0.70

oldown

0.70

long

0.68

orial

0.68

 WARRANT

0.67

sect

0.65

Activations Density 0.102%

references to time durations, particularly mentioning years and decades

references to time durations, particularly in years and months

No Comments

No Known Activations