INDEX

Explanations

punctuation marks

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

legal and regulatory terms or phrases

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ģĸ

-0.84

ĸļ

-0.77

Ĥİ

-0.73

ļéĨĴ

-0.72

ĨĴ

-0.71

Ļ½

-0.70

¬¼

-0.67

cale

-0.66

hower

-0.66

oward

-0.65

POSITIVE LOGITS

 libraries

0.99

 including

0.97

 magazines

0.95

 journals

0.94

 powd

0.93

drivers

0.93

 sauces

0.92

 bridges

0.90

 wallets

0.90

 factories

0.90

Activations Density 0.282%

punctuation marks

legal and regulatory terms or phrases

No Comments

No Known Activations