INDEX

Explanations

information related to the economic status, geography, and statistics of countries

oai_token-act-pair · gpt-3.5-turbo

references to countries, their economies, and comparative statistics

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

IFrame

Link

Negative Logits

 solic

-0.57

 minimized

-0.52

 jurors

-0.52

 inaction

-0.52

 Acting

-0.52

 omission

-0.50

 aloud

-0.50

 risked

-0.49

 texted

-0.48

 solicit

-0.48

POSITIVE LOGITS

quartered

0.79

 geographically

0.72

 continent

0.65

 economically

0.62

 biological

0.61

 populous

0.61

region

0.61

 industrialized

0.60

aceae

0.60

 birthplace

0.59

Activations Density 2.724%

information related to the economic status, geography, and statistics of countries

references to countries, their economies, and comparative statistics

No Known Activations