INDEX

Explanations

positions or titles of authority or leadership, such as "pope," "CEO," or "president."

oai_token-act-pair · gpt-3.5-turbo

terms related to leadership positions and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Consumers

-0.70

doors

-0.69

 Publishers

-0.67

 Furn

-0.61

 Dragons

-0.61

atters

-0.61

 Horses

-0.59

 Trails

-0.58

 Dreams

-0.58

 Clouds

-0.58

POSITIVE LOGITS

 whom

1.15

who

1.05

who

1.01

 persona

1.00

 whose

0.90

ship

0.88

ial

0.87

hunt

0.86

 named

0.84

dom

0.83

Activations Density 0.384%

positions or titles of authority or leadership, such as "pope," "CEO," or "president."

terms related to leadership positions and titles

No Comments

No Known Activations