INDEX

Explanations

proper nouns starting with 'Ver'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Ver" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

»Ĵ

-0.82

utics

-0.70

assetsadobe

-0.70

ħĭ

-0.68

 Sparrow

-0.67

ĩ

-0.65

cffffcc

-0.65

ollo

-0.64

OWER

-0.63

 Lovecraft

-0.63

POSITIVE LOGITS

dict

1.15

Ver

1.04

ifying

0.99

bal

0.98

tex

0.96

ified

0.95

ver

0.91

million

0.90

itas

0.89

de

0.89

Activations Density 0.020%

proper nouns starting with 'Ver'

occurrences of the name "Ver" in various contexts

No Comments

No Known Activations