INDEX

Explanations

accurate information

oai_token-act-pair · gpt-3.5-turbo

phrases related to accuracy

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

horn

-0.81

hedon

-0.75

loo

-0.72

#$#$

-0.71

osphere

-0.71

AIN

-0.70

inki

-0.69

 Amon

-0.68

 Pharma

-0.68

hov

-0.67

POSITIVE LOGITS

 portrayal

1.08

 depiction

1.00

uracy

0.93

 representation

0.91

 depictions

0.87

 estim

0.86

 accuracy

0.86

 reproduction

0.86

imating

0.85

imated

0.85

Activations Density 0.062%

accurate information

phrases related to accuracy

No Comments

No Known Activations