INDEX

Explanations

visual elements or objects mentioned in the document

oai_token-act-pair · gpt-3.5-turbo

key concepts related to various statistics, objects, and phenomena

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

anwhile

-0.67

itant

-0.57

é¾įåĸļå£«

-0.57

 Democr

-0.55

 Clockwork

-0.53

Interstitial

-0.53

)).

-0.51

ĪĴ

-0.49

perate

-0.49

local

-0.49

POSITIVE LOGITS

 consists

0.60

 comprises

0.56

 involves

0.56

 belongs

0.56

 imaginable

0.55

 exists

0.55

 âĢº

0.54

 species

0.52

 recip

0.52

 solution

0.52

Activations Density 0.741%

visual elements or objects mentioned in the document

key concepts related to various statistics, objects, and phenomena

No Comments

No Known Activations