INDEX

Explanations

terms related to extreme or high-intensity experiences or products

oai_token-act-pair · gpt-3.5-turbo

references to the word "Extreme" and related concepts

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

inson

-0.74

matically

-0.71

add

-0.67

yll

-0.67

rums

-0.67

omething

-0.66

olson

-0.65

 externalToEVAOnly

-0.65

¶æ

-0.65

tid

-0.64

POSITIVE LOGITS

 Edition

1.04

 Packs

1.04

 Warfare

1.03

 Plus

1.02

 Mode

1.01

 Series

1.00

 Catalog

0.97

 Points

0.95

 Cards

0.94

 Rules

0.94

Activations Density 0.072%

terms related to extreme or high-intensity experiences or products

references to the word "Extreme" and related concepts

No Comments

No Known Activations