INDEX

Explanations

phrases indicating examples or specifics

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a list or collection of various elements or facts

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

ocene

-0.75

ature

-0.75

jin

-0.69

 Riders

-0.68

VG

-0.66

OK

-0.63

eways

-0.62

ocent

-0.61

brook

-0.61

OK

-0.61

POSITIVE LOGITS

 transpired

0.81

properties

0.74

 pertaining

0.72

tions

0.71

 Schr

0.71

Ø³

0.70

worldly

0.70

nesses

0.70

Ø©

0.67

 includ

0.65

Activations Density 0.026%

phrases indicating examples or specifics

phrases that indicate a list or collection of various elements or facts

No Comments

No Known Activations