INDEX

Explanations

non-English characters and words

oai_token-act-pair · gpt-3.5-turbo

specific sequences of characters and special symbols, possibly reflecting encoding or formatting issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

onomy

-0.83

 bonded

-0.70

 poaching

-0.69

ortium

-0.68

ierrez

-0.66

 Hamm

-0.66

espie

-0.65

 reluct

-0.64

osaurs

-0.64

omez

-0.63

POSITIVE LOGITS

¹

1.54

³

1.52

º

1.51

¶

1.48

¼

1.46

²

1.46

±

1.44

¿

1.39

´

1.37

»

1.32

Activations Density 0.015%

non-English characters and words

specific sequences of characters and special symbols, possibly reflecting encoding or formatting issues

No Comments

No Known Activations