INDEX

Explanations

words related to quality assessment, pointing out imperfections or incompleteness

oai_token-act-pair · gpt-3.5-turbo

words related to imperfections and incompleteness

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

phasis

-0.71

CU

-0.70

UNCH

-0.70

aternity

-0.69

restling

-0.69

ablishment

-0.69

lua

-0.67

issue

-0.66

calling

-0.66

 Marriott

-0.65

POSITIVE LOGITS

 imperfect

0.98

ioned

0.86

ions

0.86

kered

0.78

 incomplete

0.76

nesses

0.76

ities

0.73

pse

0.72

uous

0.70

spect

0.69

Activations Density 0.038%

words related to quality assessment, pointing out imperfections or incompleteness

words related to imperfections and incompleteness

No Comments

No Known Activations