INDEX

Explanations

proper nouns related to names

oai_token-act-pair · gpt-3.5-turbo

names or terms associated with individuals involved in significant contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Rated

-0.79

andals

-0.70

rations

-0.70

urgy

-0.68

ittal

-0.68

Interstitial

-0.67

apping

-0.65

uers

-0.65

Balt

-0.64

apped

-0.63

POSITIVE LOGITS

hee

1.43

gee

1.38

ffe

0.96

zee

0.88

zza

0.81

ze

0.78

jee

0.78

Wee

0.78

erness

0.77

zeb

0.77

Activations Density 0.011%

proper nouns related to names

names or terms associated with individuals involved in significant contexts

No Comments

No Known Activations