INDEX

Explanations

phrases related to standard or expected situations

oai_token-act-pair · gpt-3.5-turbo

references to routine or expected behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

zon

-0.86

vic

-0.74

 Rica

-0.73

PAC

-0.68

arate

-0.66

ÄŁ

-0.65

ittees

-0.64

odan

-0.64

ï¸ı

-0.63

wic

-0.63

POSITIVE LOGITS

osphere

0.83

 tendency

0.80

 thing

0.77

est

0.75

 term

0.75

 antidote

0.75

 picture

0.74

 populace

0.73

 notion

0.73

cients

0.71

Activations Density 0.142%

phrases related to standard or expected situations

references to routine or expected behaviors

No Comments

No Known Activations