INDEX

Explanations

terms related to geopolitics, specifically focusing on diplomatic relationships and conflicts in various regions around the world

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Canaver

-0.74

]'

-0.67

 Meng

-0.67

 Guan

-0.66

 oneself

-0.66

amsung

-0.66

uador

-0.65

thora

-0.65

 Tuls

-0.65

KER

-0.65

POSITIVE LOGITS

 counterparts

1.14

 selves

0.96

 counterpart

0.90

 brethren

0.85

mates

0.81

 holdings

0.81

 buddies

0.80

 neighbors

0.76

 woes

0.76

 overl

0.74

Activations Density 3.220%

terms related to geopolitics, specifically focusing on diplomatic relationships and conflicts in various regions around the world

No Comments

No Known Activations