INDEX

Explanations

phrases related to time durations and positions within a hierarchy or series

oai_token-act-pair · gpt-3.5-turbo

mentions of specific roles or positions held over significant periods of time

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ansk

-0.73

lement

-0.72

cms

-0.70

insk

-0.64

ventus

-0.63

ANT

-0.62

Zup

-0.61

 ILCS

-0.61

kW

-0.61

ulence

-0.60

POSITIVE LOGITS

 captivity

0.96

 lowly

0.72

 stint

0.71

 tenure

0.69

 accrued

0.68

blem

0.67

 active

0.67

 adolesc

0.67

 illustrious

0.66

 career

0.64

Activations Density 0.320%

phrases related to time durations and positions within a hierarchy or series

mentions of specific roles or positions held over significant periods of time

No Comments

No Known Activations