INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and titles

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

assetsadobe

-0.68

::::::::

-0.58

 FedEx

-0.57

 physician

-0.55

credit

-0.54

 msec

-0.53

hement

-0.52

 Medicare

-0.52

 partName

-0.52

 "$:/

-0.51

POSITIVE LOGITS

usha

0.72

zon

0.71

ween

0.71

anus

0.68

ipers

0.65

hovah

0.63

iple

0.63

Champ

0.63

itars

0.62

igon

0.62

Activations Density 0.411%

proper nouns or names

proper nouns, particularly names and titles

No Comments

No Known Activations