INDEX

Explanations

phrases related to initiating or beginning actions

oai_token-act-pair · gpt-3.5-turbo

instances of the word 'start' and its variations

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

 entirety

-0.74

obi

-0.69

illard

-0.66

phy

-0.65

ighth

-0.64

itsch

-0.64

 wrought

-0.62

pedia

-0.62

ocene

-0.60

acho

-0.59

POSITIVE LOGITS

 anew

1.03

nings

0.85

starting

0.79

 behaving

0.76

 raining

0.73

strap

0.73

ribune

0.72

rek

0.69

ners

0.69

around

0.67

Activations Density 0.071%

phrases related to initiating or beginning actions

instances of the word 'start' and its variations

No Comments

No Known Activations