INDEX

Explanations

terms indicating complexity or difficulty in a situation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "complicated" and related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ablishment

-0.81

vation

-0.79

uin

-0.77

PU

-0.77

ificantly

-0.76

inals

-0.76

apons

-0.74

inth

-0.74

guyen

-0.74

emp

-0.73

POSITIVE LOGITS

 complicate

0.89

 complicated

0.88

 convoluted

0.76

 adolesc

0.72

 unnecess

0.72

 matters

0.71

 misunderstanding

0.70

 baff

0.69

 misunderstand

0.68

ioned

0.68

Activations Density 0.033%

terms indicating complexity or difficulty in a situation

instances of the word "complicated" and related contexts

No Comments

No Known Activations