INDEX

Explanations

words ending with "-ers"

oai_token-act-pair · gpt-3.5-turbo

terms that refer to groups of people or classifications

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

ADRA

-0.72

SIGN

-0.71

 forfeiture

-0.69

URRENT

-0.65

SPONSORED

-0.62

ournal

-0.62

PUT

-0.62

WR

-0.61

ISON

-0.61

 conviction

-0.61

POSITIVE LOGITS

mith

1.22

pace

1.12

paces

1.10

ucker

1.06

linger

1.05

haw

1.00

cream

0.97

ystem

0.96

peed

0.95

erker

0.91

Activations Density 0.045%

words ending with "-ers"

terms that refer to groups of people or classifications

No Comments

No Known Activations