INDEX

Explanations

mentions of laboratory work or lab-related activities

oai_token-act-pair · gpt-3.5-turbo

mentions of laboratory activities and settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

theless

-0.74

lihood

-0.68

 Masquerade

-0.65

 Resolution

-0.65

cffffcc

-0.64

 Shades

-0.64

Vote

-0.63

thood

-0.63

BOOK

-0.63

 Leilan

-0.61

POSITIVE LOGITS

rador

1.41

elling

1.32

orer

1.21

yrinth

1.03

lab

1.01

elled

0.96

lab

0.93

ysis

0.92

orers

0.91

rosse

0.90

Activations Density 0.012%

mentions of laboratory work or lab-related activities

mentions of laboratory activities and settings

No Comments

No Known Activations