INDEX

Explanations

words related to things or individuals that are captivating or enthralling

oai_token-act-pair · gpt-3.5-turbo

references to capturing or seizures in various contexts

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

 Centauri

-0.68

 paternity

-0.68

DAY

-0.67

WAYS

-0.66

 Shattered

-0.66

 prone

-0.66

 Tend

-0.66

 Patriot

-0.65

 onwards

-0.64

 donor

-0.64

POSITIVE LOGITS

ivating

1.30

aining

1.26

ains

1.20

ained

1.20

ions

1.14

ivated

1.11

iors

1.10

oded

1.09

ors

1.06

urable

1.04

Activations Density 0.021%

words related to things or individuals that are captivating or enthralling

references to capturing or seizures in various contexts

No Comments

No Known Activations