INDEX

Explanations

phrases related to traditional or standard practices

oai_token-act-pair · gpt-3.5-turbo

references to conventional designs and practices

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

oning

-0.78

gur

-0.76

oran

-0.72

haw

-0.71

hop

-0.68

hoff

-0.67

ander

-0.66

han

-0.64

 Dalai

-0.64

 Wanted

-0.63

POSITIVE LOGITS

 wisdom

1.04

ventional

0.96

etheless

0.87

 conventional

0.86

ually

0.78

ization

0.77

aneously

0.76

nesday

0.76

idad

0.76

arily

0.75

Activations Density 0.008%

phrases related to traditional or standard practices

references to conventional designs and practices

No Comments

No Known Activations