INDEX

Explanations

names or proper nouns

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and places

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Marketable

-0.66

"\

-0.62

gra

-0.57

\'

-0.52

 [âĢ¦]

-0.51

assetsadobe

-0.51

.........

-0.50

 grain

-0.49

 wheat

-0.49

Gle

-0.49

POSITIVE LOGITS

escription

0.74

isSpecial

0.67

aditional

0.66

hovah

0.65

ventus

0.64

mob

0.63

senal

0.63

ThumbnailImage

0.63

warts

0.63

inav

0.62

Activations Density 0.416%

names or proper nouns

proper nouns, particularly names and places

No Comments

No Known Activations