INDEX

Explanations

mentions of "Lab," possibly a reference or abbreviation for a laboratory or research facility

oai_token-act-pair · gpt-3.5-turbo

mentions of a specific laboratory or lab-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Marketable

-0.87

theless

-0.78

DIT

-0.72

ãģį

-0.71

 odds

-0.71

ãģ®éŃĶ

-0.70

éĹĺ

-0.69

å¹

-0.69

 Oaks

-0.67

 BASE

-0.66

POSITIVE LOGITS

rador

1.24

yrinth

1.23

elled

1.21

eled

1.15

orers

1.11

lab

1.03

elling

0.97

emark

0.95

els

0.95

Lab

0.94

Activations Density 0.007%

mentions of "Lab," possibly a reference or abbreviation for a laboratory or research facility

mentions of a specific laboratory or lab-related terms

No Comments

No Known Activations

mentions of "Lab," possibly a reference or abbreviation for a laboratory or research facility

mentions of a specific laboratory or lab-related terms

No Comments

No Known Activations