INDEX

Explanations

occurrences of the year 2003

oai_token-act-pair · gpt-3.5-turbo

references to the year 2003

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

place

-0.69

ymes

-0.69

BOOK

-0.68

pherd

-0.66

ledged

-0.66

hop

-0.64

powers

-0.62

bow

-0.62

ebook

-0.62

stakes

-0.62

POSITIVE LOGITS

å¹

0.81

-'

0.79

ĸļ

0.69

ãĥĥãĥī

0.68

 vintage

0.67

Fuk

0.65

iens

0.63

iatric

0.63

 onwards

0.62

ãĥ³ãĤ¸

0.61

Activations Density 0.022%

occurrences of the year 2003

references to the year 2003

No Comments

No Known Activations