INDEX

Explanations

proper nouns or specific entities in various contexts

oai_token-act-pair · gpt-3.5-turbo

the article "the" indicating specific subjects or topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Ò

-0.82

thood

-0.79

 because

-0.76

aba

-0.72

leeve

-0.70

eno

-0.67

bg

-0.67

Ã§a

-0.66

 whilst

-0.65

phal

-0.64

POSITIVE LOGITS

 slightest

1.09

 entire

1.07

 simplest

1.04

resa

1.03

 latter

1.01

 entirety

1.01

 biggest

1.00

oret

1.00

 vast

0.98

 majority

0.97

Activations Density 0.273%

proper nouns or specific entities in various contexts

the article "the" indicating specific subjects or topics

No Comments

No Known Activations