INDEX

Explanations

mentions and references to the country "Pakistan."

oai_token-act-pair · gpt-3.5-turbo

mentions of Pakistan

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

Not in Any Lists

No Comments

Negative Logits

mble

-0.84

aunder

-0.83

umbnails

-0.75

 Bucc

-0.71

uers

-0.71

iannopoulos

-0.68

yson

-0.68

Lys

-0.68

ipel

-0.67

llo

-0.64

POSITIVE LOGITS

istani

1.47

Pakistan

0.89

istan

0.86

 Taliban

0.85

abad

0.83

 Pakistan

0.82

 Karachi

0.77

isi

0.74

 Sharif

0.74

 Islamabad

0.72

Activations Density 0.021%

mentions and references to the country "Pakistan."

mentions of Pakistan

No Comments

No Known Activations