INDEX

Explanations

adjectives related to quantity or degree

oai_token-act-pair · gpt-3.5-turbo

instances of immediate responses or reactions to requests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 helicop

-0.59

 challeng

-0.58

oppable

-0.55

 disadvant

-0.54

abee

-0.52

abul

-0.52

renheit

-0.52

wcs

-0.51

 nearest

-0.51

 corrid

-0.51

POSITIVE LOGITS

\":

0.67

 Released

0.58

 largeDownload

0.58

Pwr

0.57

)?

0.56

 leaps

0.55

':

0.54

 OnePlus

0.54

 Flavoring

0.54

 partName

0.50

Activations Density 0.919%

adjectives related to quantity or degree

instances of immediate responses or reactions to requests

No Comments

No Known Activations