INDEX

Explanations

mentions of 'Wizard of Oz'

oai_token-act-pair · gpt-3.5-turbo

references to elements and characters from "The Wizard of Oz."

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

veland

-0.70

forth

-0.67

isSpecialOrderable

-0.59

stretched

-0.59

ĸļ

-0.57

 trave

-0.55

 Tribe

-0.55

 disciplined

-0.55

 bond

-0.54

 Weston

-0.54

POSITIVE LOGITS

glers

0.78

»Ĵ

0.62

allery

0.60

 abound

0.58

 Gleaming

0.58

 Creatures

0.58

zsche

0.55

Sov

0.55

 guiActiveUn

0.54

ãĤ©

0.54

Activations Density 1.389%

mentions of 'Wizard of Oz'

references to elements and characters from "The Wizard of Oz."

No Comments

No Known Activations