INDEX

Explanations

words related to the Star Wars franchise

oai_token-act-pair · gpt-3.5-turbo

mentions of the "Star Wars" franchise

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

onym

-0.86

onyms

-0.77

eret

-0.76

orative

-0.74

uckland

-0.71

ridges

-0.70

ebin

-0.69

itute

-0.69

odox

-0.68

ISON

-0.68

POSITIVE LOGITS

 Kenobi

0.95

 Awakens

0.94

âĦ¢:

0.93

 Odyssey

0.89

 Adventures

0.89

 Â®

0.87

 trilogy

0.87

âĦ¢

0.86

 Rebels

0.83

 Theme

0.82

Activations Density 0.026%

words related to the Star Wars franchise

mentions of the "Star Wars" franchise

No Comments

No Known Activations