INDEX

Explanations

phrases related to something being out or finished

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "out" and variations of being "off."

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

Previous

-0.74

gemony

-0.72

 Presents

-0.67

odies

-0.65

 avoids

-0.63

anship

-0.63

 transitions

-0.63

SHIP

-0.63

 VIDEOS

-0.62

 relates

-0.62

POSITIVE LOGITS

fitted

0.83

rated

0.75

enced

0.72

going

0.72

omorphic

0.71

matched

0.70

gged

0.70

achable

0.68

proof

0.67

raged

0.67

Activations Density 0.197%

phrases related to something being out or finished

occurrences of the word "out" and variations of being "off."

No Comments

No Known Activations