INDEX

Explanations

mentions of updates or changes in information

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

":[{"

-0.85

pled

-0.76

stood

-0.71

ften

-0.70

strings

-0.70

-0.69

 Haku

-0.68

kees

-0.68

pling

-0.68

soDeliveryDate

-0.67

POSITIVE LOGITS

 siege

0.68

Updated

0.68

Posted

0.68

 Opposition

0.68

 timestamp

0.65

 Coverage

0.63

 Explan

0.62

 millenn

0.61

 Transcript

0.61

apt

0.60

Activations Density 0.016%

recently updated information

mentions of updates or changes in information

No Comments

No Known Activations