INDEX

Explanations

places and locations such as streets, parks, universities, and theaters

oai_token-act-pair · gpt-3.5-turbo

locations and their significance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

enegger

-0.73

Äĩ

-0.72

Downloadha

-0.72

etheless

-0.72

*/(

-0.71

soDeliveryDate

-0.68

 fingerprints

-0.66

 Saudis

-0.65

 deleted

-0.64

 expended

-0.64

POSITIVE LOGITS

 Meadows

0.94

opolis

0.90

 Village

0.88

Aren

0.86

 Creek

0.86

bury

0.85

 Meadow

0.82

town

0.78

 Avenue

0.78

 Falls

0.77

Activations Density 0.937%

places and locations such as streets, parks, universities, and theaters

locations and their significance in various contexts

No Comments

No Known Activations