INDEX

Explanations

prepositions indicating location

oai_token-act-pair · gpt-3.5-turbo

phrases indicating position or location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anship

-0.73

ories

-0.72

vari

-0.71

iple

-0.70

/-

-0.69

allow

-0.65

ments

-0.64

ldom

-0.63

 perman

-0.63

intend

-0.63

POSITIVE LOGITS

cue

0.74

 doorstep

0.69

!:

0.67

soDeliveryDate

0.67

çĶ°

0.64

 noses

0.62

enegger

0.61

 earthqu

0.61

hovah

0.59

 Grimes

0.59

Activations Density 0.109%

prepositions indicating location

phrases indicating position or location

No Comments

No Known Activations