INDEX

Explanations

phrases indicating uncertainty or questioning

oai_token-act-pair · gpt-3.5-turbo

inquiries or expressions of uncertainty regarding specific topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

âĿ

-0.76

aukee

-0.75

 McCann

-0.72

 reperto

-0.71

 Corpus

-0.67

 Cros

-0.63

istries

-0.62

 Crom

-0.62

bley

-0.61

 âī

-0.60

POSITIVE LOGITS

 minimize

0.79

 disperse

0.78

yx

0.77

wered

0.76

 infinity

0.76

ingu

0.73

 lessen

0.72

 justify

0.71

 blame

0.71

 prevent

0.71

Activations Density 0.038%

phrases indicating uncertainty or questioning

inquiries or expressions of uncertainty regarding specific topics

No Comments

No Known Activations