INDEX

Explanations

abbreviated titles or initials in a specific format

oai_token-act-pair · gpt-3.5-turbo

acronyms or abbreviations related to organizations or entities

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

zzle

-0.68

\":

-0.67

 gorilla

-0.67

--------------------------------------------------------

-0.65

EStream

-0.64

tenance

-0.63

ãĤ°

-0.62

enance

-0.62

vag

-0.61

âĶĢâĶĢ

-0.61

POSITIVE LOGITS

SA

1.24

RC

1.20

FA

1.15

CA

1.13

SC

1.12

WA

1.10

IC

1.10

FG

1.09

LA

1.09

IA

1.08

Activations Density 0.144%

abbreviated titles or initials in a specific format

acronyms or abbreviations related to organizations or entities

No Comments

No Known Activations