INDEX

Explanations

phrases indicating a conditional statement

oai_token-act-pair · gpt-3.5-turbo

the word "that" 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rior

-0.71

Merit

-0.70

emis

-0.69

rypt

-0.67

greg

-0.66

asures

-0.65

izont

-0.64

Shar

-0.63

cycles

-0.63

IAS

-0.63

POSITIVE LOGITS

 happens

1.02

 happened

1.01

 translates

0.95

 pesky

0.92

 occurs

0.90

 mattered

0.90

 entails

0.90

 occurred

0.89

 culminated

0.86

 contradicts

0.84

Activations Density 0.177%

phrases indicating a conditional statement

the word "that" in various contexts

No Comments

No Known Activations