INDEX

Explanations

names of geographical locations or historical figures, particularly related to Vikings and historical events

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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

inventoryQuantity

-0.66

anooga

-0.65

eworks

-0.63

aminer

-0.61

nect

-0.58

ocard

-0.58

nington

-0.56

ITNESS

-0.56

boards

-0.56

Attach

-0.55

POSITIVE LOGITS

ril

0.75

rils

0.67

hal

0.62

VEN

0.61

 Yards

0.60

bard

0.58

heimer

0.57

 Nord

0.57

 Rover

0.56

 Judah

0.56

Activations Density 6.629%

names of geographical locations or historical figures, particularly related to Vikings and historical events

No Comments

No Known Activations