INDEX

Explanations

terms related to the ocean or bodies of water

oai_token-act-pair · gpt-3.5-turbo

references to the ocean

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Reloaded

-0.70

puff

-0.68

TI

-0.67

TOP

-0.66

ijah

-0.66

NER

-0.65

Madison

-0.64

oulder

-0.63

POS

-0.63

nder

-0.63

POSITIVE LOGITS

front

1.14

ographer

1.07

ographic

1.03

 basin

1.02

 liner

1.01

ic

0.96

ographers

0.93

 Ocean

0.93

arium

0.91

 ocean

0.87

Activations Density 0.055%

terms related to the ocean or bodies of water

references to the ocean

No Comments

No Known Activations