INDEX

Explanations

references to characters and elements from the Star Wars universe

oai_token-act-pair · gpt-3.5-turbo

references to the Jedi and their related characters or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Vog

-0.67

iard

-0.63

esters

-0.63

IGF

-0.62

debian

-0.62

iP

-0.62

@@

-0.62

anguages

-0.61

LIA

-0.61

trak

-0.61

POSITIVE LOGITS

 Skywalker

1.17

 Awakens

0.96

 Vader

0.95

 Kenobi

0.94

 Trooper

0.87

 Solo

0.86

 Rebels

0.85

 lightsaber

0.82

 trooper

0.82

 Leia

0.79

Activations Density 0.130%

references to characters and elements from the Star Wars universe

references to the Jedi and their related characters or concepts

No Comments

No Known Activations