INDEX

Explanations

words related to the word "song"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "ong"

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

è¦ļéĨĴ

-0.75

 Goat

-0.70

 NASCAR

-0.67

ä»£

-0.66

 Avalanche

-0.66

Pwr

-0.65

SPD

-0.63

 Brees

-0.63

éĹĺ

-0.63

ABE

-0.62

POSITIVE LOGITS

ong

1.23

ratulations

1.03

regate

0.94

atana

0.92

mong

0.92

jiang

0.91

lasses

0.90

ueless

0.87

ering

0.87

erman

0.83

Activations Density 0.008%

words related to the word "song"

occurrences of the substring "ong"

No Known Activations