INDEX

Explanations

mentions of the state of Nebraska

oai_token-act-pair · gpt-3.5-turbo

references to the state of Nebraska

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 analyse

-0.67

 analys

-0.65

 learnt

-0.65

 organise

-0.62

 arte

-0.62

 favour

-0.62

bish

-0.61

bies

-0.61

 apologise

-0.61

abil

-0.60

POSITIVE LOGITS

 Nebraska

2.46

 Wyoming

2.41

 Wisconsin

2.35

 Idaho

2.20

Wisconsin

2.20

 Vermont

2.20

 Louisiana

2.16

 Illinois

2.13

 Connecticut

2.12

 Arkansas

2.11

Activations Density 0.022%

mentions of the state of Nebraska

references to the state of Nebraska

No Comments

No Known Activations