INDEX

Explanations

phrases related to opting in or out of subscriptions or services

oai_token-act-pair · gpt-3.5-turbo

phrases that reference the concept of time or temporal conditions

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

avorite

-0.92

irt

-0.70

arte

-0.67

alach

-0.67

irts

-0.66

riad

-0.65

inav

-0.65

ussed

-0.65

ging

-0.64

uador

-0.63

POSITIVE LOGITS

frames

1.05

 periods

0.80

 gestation

0.79

 intervals

0.78

 cycle

0.77

frame

0.76

 horizon

0.75

zone

0.74

 glance

0.74

cale

0.71

Activations Density 0.048%

phrases related to opting in or out of subscriptions or services

phrases that reference the concept of time or temporal conditions

No Comments

No Known Activations