INDEX

Explanations

phrases related to political commentary

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "Y" in various contexts

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

 Creed

-0.68

 rested

-0.68

 Inquis

-0.63

ities

-0.61

 Wonderland

-0.61

 doub

-0.59

 Albion

-0.58

ãĥ¼ãĥĨãĤ£

-0.57

Sno

-0.57

 à¤

-0.56

POSITIVE LOGITS

outh

1.33

orkshire

1.33

outube

1.31

ahoo

1.31

ield

1.27

OUR

1.22

ORK

1.13

east

1.13

EAR

1.12

oga

1.11

Activations Density 0.024%

phrases related to political commentary

occurrences of the letter "Y" in various contexts

No Comments

No Known Activations