INDEX

Explanations

names of individuals or entities

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 snipp

-0.57

 Flavoring

-0.55

Yug

-0.54

 wakes

-0.52

ocaust

-0.52

Asset

-0.51

 Morty

-0.51

AND

-0.51

)</

-0.51

POSITIVE LOGITS

 respectively

1.63

 alike

1.29

 jointly

1.13

both

0.99

each

0.97

 mutually

0.91

 together

0.91

 respective

0.88

 both

0.86

together

0.83

Activations Density 0.227%

names of individuals or entities

proper nouns, particularly names of people

No Comments

No Known Activations