INDEX

Explanations

mentions of the name "Ale" followed by a number indicating the strength of activation

oai_token-act-pair · gpt-3.5-turbo

references to "Ale" beer types or brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

-0.91

ãĤ¼ãĤ¦ãĤ¹

-0.87

ä¹ĭ

-0.85

ãģį

-0.74

 Everyday

-0.69

ãģı

-0.68

aneously

-0.65

CFR

-0.64

ledged

-0.64

ãĥķãĤ©

-0.64

POSITIVE LOGITS

jandro

1.24

ppo

0.98

Ale

0.94

lette

0.94

oga

0.90

rique

0.87

terness

0.86

ogan

0.83

thia

0.82

vin

0.81

Activations Density 0.006%

mentions of the name "Ale" followed by a number indicating the strength of activation

references to "Ale" beer types or brands

No Comments

No Known Activations