INDEX

Explanations

instances where the subject is "thinking" or considering something

oai_token-act-pair · gpt-3.5-turbo

first-person pronouns and expressions of personal thoughts or experiences

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

adra

-0.71

mma

-0.68

>>\

-0.68

 Nanto

-0.66

-0.65

è¦ļéĨĴ

-0.64

 Regions

-0.63

mentioned

-0.62

-0.61

POSITIVE LOGITS

 invincible

0.79

 unbeat

0.75

 harmless

0.68

 joking

0.66

 Bout

0.65

 innocuous

0.63

 safest

0.63

 immune

0.62

 kindred

0.61

 Rack

0.61

Activations Density 0.179%

instances where the subject is "thinking" or considering something

first-person pronouns and expressions of personal thoughts or experiences

No Comments

No Known Activations