INDEX

Explanations

prepositions and location-related words

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate location or positioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

-0.72

vari

-0.69

impro

-0.68

ories

-0.65

aea

-0.64

ŃĶ

-0.63

escal

-0.63

rug

-0.63

intend

-0.63

ldom

-0.63

POSITIVE LOGITS

cue

0.95

 doorstep

0.72

 center

0.68

!:

0.67

!.

0.65

 front

0.62

 centre

0.62

 borders

0.61

 noses

0.60

soDeliveryDate

0.59

Activations Density 0.057%

prepositions and location-related words

phrases that indicate location or positioning

No Comments

No Known Activations