INDEX

Explanations

words related to minerals or chemical compounds

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "min" 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 @ 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

 Crusade

-0.75

enegger

-0.73

master

-0.67

red

-0.65

riter

-0.61

 raven

-0.61

 Compass

-0.60

hemoth

-0.60

 razor

-0.59

keyes

-0.59

POSITIVE LOGITS

nesota

1.34

utes

1.29

ority

1.04

neapolis

1.02

otaur

0.99

isters

0.99

iatures

0.97

imal

0.91

ister

0.91

imize

0.88

Activations Density 0.010%

words related to minerals or chemical compounds

mentions of the word "min" in various contexts

No Comments

No Known Activations