INDEX

Explanations

phrases depicting physical locations where someone is standing

oai_token-act-pair · gpt-3.5-turbo

the phrase "standing 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 redes

-0.67

DL

-0.64

elf

-0.64

essor

-0.64

killed

-0.63

catentry

-0.61

llor

-0.61

soever

-0.60

=""

-0.59

ŀ

-0.59

POSITIVE LOGITS

ordinate

1.13

 accordance

1.04

 front

1.01

roads

0.95

 lieu

0.95

animate

0.94

 unison

0.92

 spite

0.91

 conjunction

0.91

clud

0.90

Activations Density 0.186%

phrases depicting physical locations where someone is standing

the phrase "standing in" in various contexts

No Comments

No Known Activations