INDEX

Explanations

references to notable figures such as leaders, icons, whistleblowers, and nominees, particularly in a political context

oai_token-act-pair · gpt-3.5-turbo

terms related to political positions and figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

MpServer

-0.79

erial

-0.75

isoft

-0.73

ignant

-0.71

wcsstore

-0.71

ciplinary

-0.70

ename

-0.68

liga

-0.67

*/(

-0.67

lez

-0.66

POSITIVE LOGITS

 Stephen

1.06

 Bruce

1.03

 Tony

1.03

 Steve

1.03

 Gina

1.02

 Otto

1.02

 Julius

1.01

 Karl

1.00

 Larry

1.00

 Robert

0.99

Activations Density 0.290%

references to notable figures such as leaders, icons, whistleblowers, and nominees, particularly in a political context

terms related to political positions and figures

No Comments

No Known Activations