INDEX

Explanations

phrases describing the uniqueness or differences between various entities

oai_token-act-pair · gpt-3.5-turbo

instances and phrases indicating comparisons or contrasts

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

quished

-0.71

then

-0.71

ileaks

-0.69

 shalt

-0.68

sin

-0.67

finished

-0.65

DragonMagazine

-0.64

pleted

-0.64

HAM

-0.63

LOG

-0.63

POSITIVE LOGITS

 terms

1.48

 regards

1.24

asm

1.18

 regard

1.10

 Terms

0.98

 determining

0.95

versely

0.92

 distinguishing

0.90

 respect

0.89

 spite

0.89

Activations Density 0.180%

phrases describing the uniqueness or differences between various entities

instances and phrases indicating comparisons or contrasts

No Comments

No Known Activations