INDEX

Explanations

words related to making decisions or choices

oai_token-act-pair · gpt-3.5-turbo

instances of the word "choose" and its variations in the context of decision-making

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

brance

-0.85

itamin

-0.68

ptoms

-0.65

forcing

-0.64

è¦ļéĨĴ

-0.64

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.63

mons

-0.62

otor

-0.62

ONY

-0.60

dfx

-0.58

POSITIVE LOGITS

 wisely

1.04

to

0.86

not

0.71

 instead

0.70

 sides

0.69

 chosen

0.66

 chose

0.66

 whichever

0.64

 randomly

0.64

eters

0.63

Activations Density 0.044%

words related to making decisions or choices

instances of the word "choose" and its variations in the context of decision-making

No Comments

No Known Activations