INDEX

Explanations

questions posed using the phrase "Can you"

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "Can you" along with variations requesting action or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ylum

-0.69

teen

-0.67

chwitz

-0.66

assic

-0.66

-0.64

yk

-0.63

senal

-0.63

 Lauder

-0.62

anamo

-0.61

gement

-0.61

POSITIVE LOGITS

 afford

1.37

 imagine

1.18

 possibly

1.05

 quantify

1.03

 realistically

1.00

 please

1.00

 foresee

0.97

 PLEASE

0.97

 feas

0.97

 conceive

0.96

Activations Density 0.037%

questions posed using the phrase "Can you"

instances of the phrase "Can you" along with variations requesting action or information

No Comments

No Known Activations