INDEX

Explanations

phrases related to legal agreements or official documents

oai_token-act-pair · gpt-3.5-turbo

references to formal agreements and arrangements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

actionDate

-0.78

ayan

-0.71

cipled

-0.71

romy

-0.68

å§«

-0.68

entimes

-0.68

axter

-0.66

DragonMagazine

-0.64

olute

-0.63

ciplinary

-0.63

POSITIVE LOGITS

 itself

0.91

 pictured

0.81

USS

0.77

 mentioned

0.75

osphere

0.75

 which

0.74

 that

0.71

 known

0.71

 depicted

0.70

 allotted

0.70

Activations Density 0.567%

phrases related to legal agreements or official documents

references to formal agreements and arrangements

No Comments

No Known Activations