INDEX

Explanations

mentions of large quantities of money

oai_token-act-pair · gpt-3.5-turbo

phrases referencing large quantities of people or amounts of money

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

imen

-0.81

mentioned

-0.69

Adv

-0.67

cial

-0.67

ãĥ¤

-0.62

iban

-0.62

Condition

-0.61

anooga

-0.61

occup

-0.59

tein

-0.59

POSITIVE LOGITS

aires

0.99

aire

0.94

 dollars

0.92

 billions

0.83

 euros

0.81

 litres

0.79

 Millions

0.79

ujah

0.78

 ILCS

0.78

 millions

0.77

Activations Density 0.027%

mentions of large quantities of money

phrases referencing large quantities of people or amounts of money

No Comments

No Known Activations