INDEX

Explanations

mentions of chief executive officers

oai_token-act-pair · gpt-3.5-turbo

terms related to corporate leadership positions, particularly those of chief executives

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

obos

-0.73

dayName

-0.72

atche

-0.68

 rive

-0.68

 convict

-0.67

ramid

-0.66

sterdam

-0.64

chwitz

-0.63

ewitness

-0.62

 degrade

-0.62

POSITIVE LOGITS

 Officer

0.74

 officer

0.74

ois

0.71

CEO

0.70

 Cyrus

0.67

doms

0.65

alties

0.65

 emer

0.63

Chief

0.63

 Equity

0.62

Activations Density 0.075%

mentions of chief executive officers

terms related to corporate leadership positions, particularly those of chief executives

No Known Activations