INDEX

Explanations

product-related terms

oai_token-act-pair · gpt-3.5-turbo

mentions of "Product" in various contexts associated with updates and descriptions

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

 Blaz

-0.68

trop

-0.67

 Brother

-0.63

 Leone

-0.61

 Peninsula

-0.60

QUEST

-0.60

CLASSIFIED

-0.59

 lone

-0.58

asons

-0.57

 Soros

-0.57

POSITIVE LOGITS

ivity

1.53

ively

1.37

ivities

1.23

iveness

1.12

ions

0.89

 packaging

0.89

Hunt

0.86

ivism

0.86

urers

0.84

istry

0.82

Activations Density 0.024%

product-related terms

mentions of "Product" in various contexts associated with updates and descriptions

No Comments

No Known Activations