INDEX

Explanations

questions or exclamations demanding attention or explanation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "What."

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

ulic

-0.72

trop

-0.67

println

-0.59

emp

-0.59

rolet

-0.58

cel

-0.58

POR

-0.58

 present

-0.57

lich

-0.56

Sport

-0.56

POSITIVE LOGITS

soever

1.33

 happens

0.98

 happened

0.97

 happ

0.91

 sorts

0.88

 kinds

0.86

 transpired

0.80

nces

0.76

 else

0.74

 constitutes

0.71

Activations Density 0.109%

questions or exclamations demanding attention or explanation

instances of the word "What."

No Comments

No Known Activations