INDEX

Explanations

provinces or cities in a specific region

oai_token-act-pair · gpt-3.5-turbo

references to cities in geopolitical contexts, particularly focusing on Tehran and Ankara

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

::::::::

-0.81

Uncommon

-0.78

Trend

-0.75

vich

-0.72

Torrent

-0.71

Norm

-0.69

ICAN

-0.68

ONSORED

-0.68

estern

-0.66

oslov

-0.66

POSITIVE LOGITS

ascus

1.19

 Lumpur

1.01

 Ankara

0.90

hran

0.84

 Aires

0.84

 Islamabad

0.82

mouth

0.82

 rall

0.80

ffiti

0.78

halla

0.77

Activations Density 0.020%

provinces or cities in a specific region

references to cities in geopolitical contexts, particularly focusing on Tehran and Ankara

No Comments

No Known Activations