INDEX

Explanations

phrases related to software or product updates

oai_token-act-pair · gpt-3.5-turbo

references to software updates or changes in versioning

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

brid

-0.72

entimes

-0.68

clud

-0.67

ancial

-0.67

enegger

-0.65

culosis

-0.65

daq

-0.62

liners

-0.62

sense

-0.60

conservancy

-0.60

POSITIVE LOGITS

 Expend

0.72

 Draco

0.71

TBA

0.68

Jr

0.66

 Basil

0.66

Jr

0.64

???

0.64

 Gerald

0.63

 Learns

0.61

VOL

0.61

Activations Density 0.212%

phrases related to software or product updates

references to software updates or changes in versioning

No Comments

No Known Activations