INDEX

Explanations

instances of the word "complicated" at varying activations

oai_token-act-pair · gpt-3.5-turbo

the concept of complexity in various contexts

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

vation

-0.86

inals

-0.80

ablishment

-0.79

PU

-0.74

OIL

-0.74

inth

-0.73

vertising

-0.71

uin

-0.71

Naz

-0.69

ILA

-0.68

POSITIVE LOGITS

 complicate

0.88

 complicated

0.87

ioned

0.79

 convoluted

0.78

 matters

0.74

 unnecess

0.73

 misunderstand

0.72

 logistical

0.71

 misunderstanding

0.70

 trig

0.70

Activations Density 0.026%

instances of the word "complicated" at varying activations

the concept of complexity in various contexts

No Comments

No Known Activations