INDEX

Explanations

phrases indicating the presence or existence of something specific within a context

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate the presence of certain substances or components

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

urai

-0.77

 Sabha

-0.70

liner

-0.67

doms

-0.66

 athlet

-0.64

economic

-0.64

laus

-0.63

 axis

-0.62

 Scythe

-0.61

fortunately

-0.61

POSITIVE LOGITS

encies

0.80

ences

0.75

ãĤ¼ãĤ¦ãĤ¹

0.74

CONT

0.73

ãĤ£

0.73

ãĤ·ãĥ£

0.72

iveness

0.70

 Contains

0.70

 contents

0.70

ÃįÃį

0.68

Activations Density 0.018%

phrases indicating the presence or existence of something specific within a context

phrases that indicate the presence of certain substances or components

No Comments

No Known Activations