INDEX

Explanations

terms related to robotic entities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "bot" and variations, indicating a focus on robotic entities or themes related to artificial intelligence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ANCE

-0.80

 Endurance

-0.74

 Sahara

-0.69

 Katrina

-0.68

ICC

-0.67

 European

-0.65

 African

-0.63

 Louisiana

-0.62

ra

-0.62

Koh

-0.62

POSITIVE LOGITS

bot

4.42

bots

3.18

Bot

2.59

bot

2.00

 bots

1.84

Bot

1.72

 Bots

1.68

bott

1.38

 Robots

1.22

borg

1.21

Activations Density 0.021%

terms related to robotic entities

occurrences of the term "bot" and variations, indicating a focus on robotic entities or themes related to artificial intelligence

No Comments

No Known Activations