INDEX

Explanations

adjectives or phrases indicating clear visibility or presence

oai_token-act-pair · gpt-3.5-turbo

expressions indicating clear visibility or clarity of a situation or state

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

bucks

-0.76

naire

-0.71

lua

-0.67

halla

-0.65

arian

-0.64

ttle

-0.63

jee

-0.63

Ã³n

-0.62

pole

-0.62

rak

-0.62

POSITIVE LOGITS

 evident

3.52

 apparent

2.03

 evidenced

1.65

 obvious

1.65

 palpable

1.54

 noticeable

1.37

 visible

1.26

 undeniable

1.24

 observable

1.22

 manifest

1.22

Activations Density 0.011%

adjectives or phrases indicating clear visibility or presence

expressions indicating clear visibility or clarity of a situation or state

No Comments

No Known Activations