INDEX

Explanations

phrases related to distance and measurement

oai_token-act-pair · gpt-3.5-turbo

special characters or symbols that appear frequently in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

gad

-0.72

 confinement

-0.71

Peb

-0.70

 venture

-0.69

 scattering

-0.69

 Sapphire

-0.68

 scatter

-0.67

 shroud

-0.67

 Dresden

-0.66

 Luxembourg

-0.65

POSITIVE LOGITS

¹

1.35

Į

1.31

º

1.26

£

1.21

»

1.19

į

1.15

ª

1.11

¤

1.08

¬

1.08

ł

1.06

Activations Density 0.145%

phrases related to distance and measurement

special characters or symbols that appear frequently in the document

No Comments

No Known Activations