INDEX

Explanations

titles of articles or papers

oai_token-act-pair · gpt-3.5-turbo

instances of the word "titled" and "entitled" indicating the title of a document or article

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

eda

-0.75

ometers

-0.72

 squared

-0.66

olson

-0.65

phthal

-0.64

Era

-0.63

arthy

-0.63

asted

-0.61

APD

-0.60

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.59

POSITIVE LOGITS

"#

0.78

pins

0.75

selves

0.73

 titled

0.73

"<

0.72

eous

0.71

forward

0.69

checks

0.67

nces

0.67

 namely

0.67

Activations Density 0.028%

titles of articles or papers

instances of the word "titled" and "entitled" indicating the title of a document or article

No Comments

No Known Activations