INDEX

Explanations

questions ending in "?" and exclamatory questions

oai_token-act-pair · gpt-3.5-turbo

interrogative sentences or questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

avorite

-0.81

 encount

-0.81

 colon

-0.75

 charism

-0.70

ady

-0.69

alist

-0.68

etheless

-0.68

 destro

-0.67

ailability

-0.66

anni

-0.66

POSITIVE LOGITS

 Surely

1.15

 Where

1.14

 Nope

1.12

Why

1.08

 Somebody

1.07

 Anyway

1.07

 Answer

1.07

?!

1.05

Huh

1.04

Isn

1.01

Activations Density 0.110%

questions ending in "?" and exclamatory questions

interrogative sentences or questions

No Comments

No Known Activations