INDEX

Explanations

articles that delve into a specific topic in detail and provide additional information for the readers

oai_token-act-pair · gpt-3.5-turbo

occurrences of the phrase "Read more."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 newcom

-0.62

 sucker

-0.60

oun

-0.60

 teasp

-0.58

[|

-0.54

 numbering

-0.53

 endeavor

-0.52

 satell

-0.52

vertisement

-0.52

 utilizing

-0.52

POSITIVE LOGITS

stars

0.69

Why

0.68

↵

0.68

 VIDEOS

0.67

âĢ¦]

0.65

Sorry

0.61

...]

0.59

gres

0.59

biz

0.58

tery

0.57

Activations Density 0.010%

articles that delve into a specific topic in detail and provide additional information for the readers

occurrences of the phrase "Read more."

No Comments

No Known Activations