INDEX

Explanations

questions starting with "Why"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Why" that express questioning or curiosity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Roller

-0.71

ages

-0.65

rop

-0.63

lator

-0.62

 puck

-0.62

ymph

-0.62

 polymorph

-0.62

 tuber

-0.62

 medic

-0.62

pocket

-0.61

POSITIVE LOGITS

soever

1.12

why

0.94

why

0.91

WHY

0.90

Why

0.86

iterranean

0.75

Why

0.75

tical

0.71

beit

0.71

ertodd

0.71

Activations Density 0.037%

questions starting with "Why"

instances of the word "Why" that express questioning or curiosity

No Comments

No Known Activations