INDEX

Explanations

information related to military conflicts and attacks

oai_token-act-pair · gpt-3.5-turbo

phrases related to military operations and incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Whitney

-0.81

 Cary

-0.80

 Barney

-0.71

 Forrest

-0.70

 Peyton

-0.69

 Avery

-0.69

 darn

-0.68

DeL

-0.68

Madison

-0.68

 Vaughn

-0.68

POSITIVE LOGITS

 Ankara

0.96

PKK

0.95

zbollah

0.93

 Nato

0.92

 ceasefire

0.91

 Kazakh

0.91

 Azerbai

0.90

istani

0.89

 Kurdish

0.89

ÄŁ

0.89

Activations Density 1.654%

information related to military conflicts and attacks

phrases related to military operations and incidents

No Comments

No Known Activations