INDEX

Explanations

proper nouns or specific names

oai_token-act-pair · gpt-3.5-turbo

names and titles associated with entities and roles

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

ollah

-0.66

olulu

-0.64

 scary

-0.64

yip

-0.64

okemon

-0.63

ppo

-0.62

 caut

-0.59

ãģĻ

-0.58

????????

-0.58

Fet

-0.58

POSITIVE LOGITS

 underwent

1.08

 undergo

0.94

 possesses

0.91

 retains

0.90

 suffers

0.89

 enjoys

0.87

 employs

0.87

 toured

0.86

 comprises

0.83

 spends

0.83

Activations Density 0.514%

proper nouns or specific names

names and titles associated with entities and roles

No Comments

No Known Activations