INDEX

Explanations

references related to specific locations or regions

oai_token-act-pair · gpt-3.5-turbo

the preposition "in" in various contexts

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

llor

-0.73

!--

-0.70

aspers

-0.69

DragonMagazine

-0.67

emis

-0.66

 Advertisement

-0.66

+++

-0.64

ogyn

-0.63

anship

-0.62

DEM

-0.61

POSITIVE LOGITS

 question

1.00

 whence

0.81

effect

0.75

 conjunction

0.74

 front

0.74

patient

0.72

 itself

0.72

ducers

0.70

ked

0.69

 lieu

0.68

Activations Density 0.510%

references related to specific locations or regions

the preposition "in" in various contexts

No Comments

No Known Activations