INDEX

Explanations

locations and phrases written on objects

oai_token-act-pair · gpt-3.5-turbo

specific items or features that are detailed in a physical description

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

WAY

-0.85

 facult

-0.80

Charges

-0.79

QUIRE

-0.74

BIL

-0.73

Phones

-0.72

 virginity

-0.71

wife

-0.70

çĦ

-0.70

================================

-0.69

POSITIVE LOGITS

 aster

0.83

 orange

0.80

RGB

0.79

pi

0.78

 marker

0.77

 pixels

0.77

 etched

0.77

 highlighted

0.77

 Doodle

0.76

 stripes

0.76

Activations Density 0.389%

locations and phrases written on objects

specific items or features that are detailed in a physical description

No Comments

No Known Activations