INDEX

Explanations

proper nouns related to popular culture, such as movie titles, TV show names, and celebrity names

oai_token-act-pair · gpt-3.5-turbo

references to cultural events or performances

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

azeera

-0.76

utenberg

-0.71

IST

-0.67

bol

-0.67

lav

-0.66

ãĤ´ãĥ³

-0.64

inventoryQuantity

-0.62

alach

-0.60

pmwiki

-0.59

ategory

-0.58

POSITIVE LOGITS

ÏĤ

0.73

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

0.69

 Horses

0.65

 Regiment

0.64

ī

0.60

III

0.60

 Remastered

0.59

Ń

0.59

 Sketch

0.59

 Shotgun

0.58

Activations Density 0.318%

proper nouns related to popular culture, such as movie titles, TV show names, and celebrity names

references to cultural events or performances

No Comments

No Known Activations