INDEX

Explanations

phrases related to armor

oai_token-act-pair · gpt-3.5-turbo

mentions of armor and protective gear

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Vide

-0.77

=-=-=-=-

-0.74

 Lakes

-0.73

present

-0.70

event

-0.70

erences

-0.67

AUD

-0.67

vous

-0.67

âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ

-0.66

cause

-0.66

POSITIVE LOGITS

 armor

1.25

 armour

1.22

 piercing

1.06

armor

0.96

 defences

0.94

 defenses

0.89

 tradem

0.88

 Armor

0.85

 penetration

0.84

anguage

0.84

Activations Density 0.006%

phrases related to armor

mentions of armor and protective gear

No Known Activations