INDEX

Explanations

phrases related to movement and action

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to taking action or movement

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

ici

-0.85

illi

-0.76

 Mason

-0.71

olitan

-0.71

-0.70

rit

-0.70

 Feder

-0.69

illian

-0.69

POSITIVE LOGITS

up

1.48

up

1.43

ups

1.31

UP

1.29

Up

1.28

Up

1.27

ups

1.24

UP

1.23

 down

1.17

down

1.11

Activations Density 0.095%

phrases related to movement and action

words and phrases related to taking action or movement

No Comments

No Known Activations