INDEX

Explanations

proper nouns indicating people in leadership roles

oai_token-act-pair · gpt-3.5-turbo

titles and roles associated with leadership and authority figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 queen

-0.74

 destro

-0.74

iscopal

-0.73

 board

-0.72

rift

-0.71

 stroke

-0.70

elf

-0.69

aver

-0.68

 maiden

-0.68

published

-0.68

POSITIVE LOGITS

 Officer

1.03

 Ambassador

0.99

 Agent

0.98

 Manager

0.95

 Accountability

0.95

 Commander

0.93

 Representative

0.93

 Leader

0.92

 Candidate

0.91

 Investigator

0.91

Activations Density 0.047%

proper nouns indicating people in leadership roles

titles and roles associated with leadership and authority figures

No Comments

No Known Activations