INDEX

Explanations

words related to armor and gear

oai_token-act-pair · gpt-3.5-turbo

references to 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

zee

-0.82

vous

-0.73

 Vide

-0.73

liam

-0.72

 Lakes

-0.71

ãĤ§

-0.69

Bee

-0.68

arak

-0.68

pled

-0.65

soDeliveryDate

-0.65

POSITIVE LOGITS

 piercing

1.05

ments

1.05

 clad

0.95

 armour

0.92

 Piercing

0.91

 armor

0.86

 worn

0.84

 thickness

0.83

clad

0.80

 defences

0.78

Activations Density 0.015%

words related to armor and gear

references to armor and protective gear

No Comments

No Known Activations