INDEX

Explanations

the word "make" or its variations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the concept of making sense or differences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rina

-0.70

thia

-0.67

 nurs

-0.66

 cautioned

-0.65

 presided

-0.64

 withd

-0.63

 imagin

-0.60

 helicop

-0.59

 diligently

-0.57

 faithfully

-0.56

POSITIVE LOGITS

 sense

1.34

hift

1.01

 headlines

0.96

 landfall

0.93

 Sense

0.90

sense

0.89

 sure

0.85

 matters

0.76

 mockery

0.75

 perfect

0.75

Activations Density 0.090%

the word "make" or its variations

phrases indicating the concept of making sense or differences

No Comments

No Known Activations